{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9959861f-5a74-427b-9ff1-168c10d68ef3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5b3838f4-99be-40b6-bf22-7ae634c6539f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !python3 -m pip install --upgrade pip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "eec4a78b-cf34-4e7a-9250-16cc91a1c09d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from transformers import (\n",
    "  HubertForCTC,\n",
    "  Wav2Vec2Processor,\n",
    "  Wav2Vec2CTCTokenizer,\n",
    "  Wav2Vec2FeatureExtractor,\n",
    "  TrainingArguments,\n",
    "  Trainer,\n",
    ")\n",
    "import torch\n",
    "from transformers import Wav2Vec2Processor\n",
    "from dataclasses import dataclass, field\n",
    "from typing import Any, Dict, List, Optional, Union\n",
    "from datasets import load_metric, concatenate_datasets, load_dataset, Audio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "20521c22-4d57-4e6d-b361-b600c97c5358",
   "metadata": {},
   "outputs": [],
   "source": [
    "@dataclass\n",
    "class DataCollatorCTCWithPadding:\n",
    "  processor: Wav2Vec2Processor\n",
    "  padding: Union[bool, str] = True\n",
    "\n",
    "  def __call__(\n",
    "    self, features: List[Dict[str, Union[List[int], torch.Tensor]]]\n",
    "  ) -> Dict[str, torch.Tensor]:\n",
    "    # split inputs and labels since they have to be of different lengths and need\n",
    "    # different padding methods\n",
    "    input_features = [{\"input_values\": feature[\"input_values\"]} for feature in features]\n",
    "    label_features = [{\"input_ids\": feature[\"labels\"]} for feature in features]\n",
    "\n",
    "    batch = self.processor.pad(\n",
    "      input_features,\n",
    "      padding=self.padding,\n",
    "      return_tensors=\"pt\",\n",
    "    )\n",
    "    with self.processor.as_target_processor():\n",
    "      labels_batch = self.processor.pad(\n",
    "        label_features,\n",
    "        padding=self.padding,\n",
    "        return_tensors=\"pt\",\n",
    "      )\n",
    "\n",
    "    # replace padding with -100 to ignore loss correctly\n",
    "    labels = labels_batch[\"input_ids\"].masked_fill(\n",
    "      labels_batch.attention_mask.ne(1), -100\n",
    "    )\n",
    "\n",
    "    batch[\"labels\"] = labels\n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0a9b6c9e-fa72-4822-b3d9-7fcb585b7b36",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Token is valid (permission: write).\n",
      "Your token has been saved in your configured git credential helpers (store).\n",
      "Your token has been saved to /root/.cache/huggingface/token\n",
      "Login successful\n"
     ]
    }
   ],
   "source": [
    "from huggingface_hub import notebook_login, login\n",
    "\n",
    "login(\"hf_token\", True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "24042af6-9380-45cb-81c9-7f21ac6c631c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/datasets/load.py:2554: FutureWarning: 'use_auth_token' was deprecated in favor of 'token' in version 2.14.0 and will be removed in 3.0.0.\n",
      "You can remove this warning by passing 'token=<use_auth_token>' instead.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4551f7a040594f61b0a125f2206e8cc9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading builder script:   0%|          | 0.00/8.19k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bd0e47b7a8bb4d9e8562429f224b641d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading readme:   0%|          | 0.00/12.7k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "58d5bd9dab234aa2a82618143daaa2bb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading extra modules:   0%|          | 0.00/3.92k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f5d19afbdee94f2886cee6b92c99c80f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading extra modules:   0%|          | 0.00/132k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f0d157ec2ea44e959c57541d03e6e127",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/17.5k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a4a6f3266e5047dc831994573c7a8c5b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.11G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2ddd845f444c4c14a0b885fe4d5780eb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.08G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6d38921189b748a59585a0e6428a756d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.01G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b08f814db5d64ccb8f2afdd9ef840382",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/432M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "dee0930c5a464464ba7160ddae283159",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/439M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3694ea604192456b8f42802693e12fb5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/13.3M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8cd553b56a334d4a81fa4b71c3fb91d6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/240M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "798f94937ace4ac9bcded4e934eedbf7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.19G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "93ac045465924f9eb9bb12030c73d39c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.09G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "71032ec09b024b308435c61aff20bb7f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.10G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8e5e1802b4a547af92abd81008a81fea",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.05G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5a85682478e54c1fba98dff237223211",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/1.06G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2cb108ba39f8411dbd93b8a2ce841916",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/228M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ab8803e908f54138acc6b2a9b86e424b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/39.3M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "31ba281d28f04199810ae95b22f26cce",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/4.77M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5c928da627484fca8f27c36cdb34f1c3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/4.65M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d40cd4383ded4d6e8468a27877278760",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/157k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "11a1d539ae414b95af9de13b04ae1802",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/2.65M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "09bd7f803ef749f094af2087d8945f89",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading data:   0%|          | 0.00/68.8M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1d3dfe6fd3b84cb6b30f8d7a61537d7d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 0it [00:00, ?it/s]\u001b[A\n",
      "Reading metadata...: 14736it [00:00, 147352.76it/s]\u001b[A\n",
      "Reading metadata...: 29699it [00:00, 148687.16it/s]\u001b[A\n",
      "Reading metadata...: 44568it [00:00, 148554.45it/s]\u001b[A\n",
      "Reading metadata...: 59463it [00:00, 148706.38it/s]\u001b[A\n",
      "Reading metadata...: 74334it [00:00, 145886.45it/s]\u001b[A\n",
      "Reading metadata...: 88932it [00:00, 144124.52it/s]\u001b[A\n",
      "Reading metadata...: 103353it [00:00, 143464.01it/s]\u001b[A\n",
      "Reading metadata...: 119180it [00:00, 145082.51it/s]\u001b[A\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c49799e936d94a93ac627c4556d4acc9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating validation split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 14495it [00:00, 147067.28it/s]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fffe9ca8a6db460bb2c0bb351c2ab7cb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating test split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 14513it [00:00, 154055.46it/s]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "44fc0e6aa07a44d28f5e19cf5f388369",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating other split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 493it [00:00, 128354.55it/s]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "39a01e63010245aaa7dd7665212b2534",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating invalidated split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 7960it [00:00, 143292.85it/s]\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "22b265a7be1642869bf4583a332acc8c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating validated split: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "Reading metadata...: 0it [00:00, ?it/s]\u001b[A\n",
      "Reading metadata...: 15618it [00:00, 156171.96it/s]\u001b[A\n",
      "Reading metadata...: 31737it [00:00, 159119.31it/s]\u001b[A\n",
      "Reading metadata...: 47649it [00:00, 155583.00it/s]\u001b[A\n",
      "Reading metadata...: 63217it [00:00, 152091.81it/s]\u001b[A\n",
      "Reading metadata...: 78440it [00:00, 151895.76it/s]\u001b[A\n",
      "Reading metadata...: 93638it [00:00, 151469.59it/s]\u001b[A\n",
      "Reading metadata...: 108790it [00:00, 150521.49it/s]\u001b[A\n",
      "Reading metadata...: 123846it [00:00, 149525.41it/s]\u001b[A\n",
      "Reading metadata...: 138801it [00:00, 146779.51it/s]\u001b[A\n",
      "Reading metadata...: 154009it [00:01, 148376.19it/s]\u001b[A\n",
      "Reading metadata...: 168857it [00:01, 146840.37it/s]\u001b[A\n",
      "Reading metadata...: 183550it [00:01, 145609.81it/s]\u001b[A\n",
      "Reading metadata...: 209653it [00:01, 148701.85it/s]\u001b[A\n"
     ]
    }
   ],
   "source": [
    "from datasets import load_dataset, load_metric, Audio\n",
    "\n",
    "common_voice_train = load_dataset(\"mozilla-foundation/common_voice_17_0\", \"ba\", split=\"train+validation\",keep_in_memory=True, trust_remote_code=True, use_auth_token=True)\n",
    "common_voice_test = load_dataset(\"mozilla-foundation/common_voice_17_0\", \"ba\", split=\"test\",keep_in_memory=True, trust_remote_code=True, use_auth_token=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "24c58316-8f4b-41f4-a42c-98c9b32e83bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import ClassLabel\n",
    "import random\n",
    "import pandas as pd\n",
    "from IPython.display import display, HTML\n",
    "\n",
    "def show_random_elements(dataset, num_examples=10):\n",
    "    assert num_examples <= len(dataset), \"Can't pick more elements than there are in the dataset.\"\n",
    "    picks = []\n",
    "    for _ in range(num_examples):\n",
    "        pick = random.randint(0, len(dataset)-1)\n",
    "        while pick in picks:\n",
    "            pick = random.randint(0, len(dataset)-1)\n",
    "        picks.append(pick)\n",
    "    \n",
    "    df = pd.DataFrame(dataset[picks])\n",
    "    display(HTML(df.to_html()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0d2eb6a6-64ff-411b-9012-be279ccbce71",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install \"soundfile>=0.12.1\" -U"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "bcc9140d-df99-4920-86fe-38733344514c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "46011fa3-13c2-4639-b978-d37022380e97",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>client_id</th>\n",
       "      <th>audio</th>\n",
       "      <th>sentence</th>\n",
       "      <th>up_votes</th>\n",
       "      <th>down_votes</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>accent</th>\n",
       "      <th>locale</th>\n",
       "      <th>segment</th>\n",
       "      <th>variant</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>96f58b0274d05b4b890c7e21fab8fab819a27c284ab68b9614a5dc3c435ed553464c27d8fa81720e0e5bca6e7fd13c8d0a3f7bcb258487312d889f4a7317b1f9</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/944fc7c543869badc9d8d8062f5e8e33351fb7826c2bd639f752d45bf1d9f1b9/ba_train_2/common_voice_ba_26163821.mp3', 'array': [9.094947017729282e-13, -7.275957614183426e-12, -1.6370904631912708e-11, -1.0459189070388675e-11, -9.094947017729282e-13, 8.185452315956354e-12, 9.549694368615746e-12, 1.0913936421275139e-11, 6.366462912410498e-12, 5.4569682106375694e-12, 7.275957614183426e-12, 1.4551915228366852e-11, 1.2732925824820995e-11, 8.185452315956354e-12, 9.094947017729282e-13, 0.0, 6.366462912410498e-12, 1.546140993013978e-11, 2.637534635141492e-11, 4.001776687800884e-11, 4.18367562815547e-11, 4.001776687800884e-11, 3.728928277269006e-11, 2.546585164964199e-11, -2.7284841053187847e-12, -3.456079866737127e-11, -6.184563972055912e-11, -7.09405867382884e-11, -7.639755494892597e-11, -8.549250196665525e-11, -8.458300726488233e-11, -6.366462912410498e-11, -1.9099388737231493e-11, 4.547473508864641e-13, -9.094947017729282e-12, -3.865352482534945e-11, -5.275069270282984e-11, -4.774847184307873e-11, -2.2737367544323206e-11, -2.000888343900442e-11, -6.275513442233205e-11, -1.1186784831807017e-10, -1.0868461686186492e-10, -8.185452315956354e-12, 1.532498572487384e-10, 2.864908310584724e-10, 3.510649548843503e-10, 4.1154635255225003e-10, 5.607034836430103e-10, 7.880771590862423e-10, 9.840732673183084e-10, 9.777068044058979e-10, 6.978098099352792e-10, 3.019522409886122e-10, -1.1823431123048067e-11, -2.637534635141492e-10, -5.966285243630409e-10, -1.0741132427938282e-09, -1.6589183360338211e-09, -2.2646418074145913e-09, -2.7303030947223306e-09, -2.9849616112187505e-09, -3.1641320674680173e-09, -3.4297045203857124e-09, -3.7630343285854906e-09, -3.997683961642906e-09, -3.952663973905146e-09, -3.613422450143844e-09, -3.1768649932928383e-09, -2.890374162234366e-09, -2.8194335754960775e-09, -2.8958311304450035e-09, -3.0831870390102267e-09, -3.335117071401328e-09, -3.6325218388810754e-09, -4.101821104995906e-09, -4.895355232292786e-09, -5.923084245296195e-09, -6.874188329675235e-09, -7.451262717950158e-09, -7.58791429689154e-09, -7.504240784328431e-09, -7.523340173065662e-09, -7.736161933280528e-09, -7.905327947810292e-09, -7.670678314752877e-09, -6.804839358665049e-09, -5.420588422566652e-09, -3.939931048080325e-09, -2.7321220841258764e-09, -1.6316334949806333e-09, -1.3369572116062045e-10, 1.9681465346366167e-09, 4.1009116102941334e-09, 5.2159521146677434e-09, 4.790308594238013e-09, 3.4287950256839395e-09, 2.241904439870268e-09, 1.724401954561472e-09, 1.4679244486615062e-09, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Был минең ҡыҙым</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>e160b36a4c95f67d0d0f35c1f0e262e3275c4ce49a92410607bd64f89a96ccfce73003ec9b45f94c1eaf91c358b3728ddcbbe62c970c2a729b39eedc5b44d296</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/944fc7c543869badc9d8d8062f5e8e33351fb7826c2bd639f752d45bf1d9f1b9/ba_train_2/common_voice_ba_26031663.mp3', 'array': [1.9645539548134407e-24, -3.799860938915471e-24, -1.9128551665288765e-24, -4.1359030627651384e-25, -6.72084247699335e-25, -5.686866711302065e-25, -2.274746684520826e-24, -4.497794580757088e-24, -4.446095792472524e-24, -3.308722450212111e-24, 2.481541837659083e-24, -8.271806125530277e-25, -8.06501097239202e-24, -2.0679515313825692e-24, -2.5332406259436473e-24, -1.2149215246872594e-24, 1.5800442169469943e-24, 2.1196503196671334e-24, -2.6366382025127757e-24, -1.1632227364026952e-24, 2.7788098702953273e-25, -6.462348535570529e-25, 1.7771458472818954e-25, 4.937234281175884e-24, 8.271806125530277e-24, 4.226375942263126e-24, 1.173562494059608e-23, 6.2038545941477076e-24, 9.228233708794715e-24, 3.677076316739631e-24, 7.005185812558453e-24, 6.814546530759123e-24, 5.686866711302065e-25, -2.3264454728053903e-25, 5.169878828456423e-26, -5.790264287871194e-24, -7.858215819253763e-24, -4.963083675318166e-24, -8.271806125530277e-25, -4.1359030627651384e-25, -3.7223127564886245e-24, -7.444625512977249e-24, -1.6543612251060553e-24, -1.6543612251060553e-23, -1.6543612251060553e-24, 1.2407709188295415e-23, 2.895132143935597e-24, -1.809457589959748e-24, -8.788794008375919e-25, -1.0081263715490025e-24, -3.5155176033503676e-24, -5.118180040171859e-24, 1.6672859221771964e-24, 3.166550782429559e-24, -1.9128551665288765e-24, -4.7748677742196744e-24, 3.7481621506309067e-25, 1.9387045606711586e-26, 2.859589226989959e-24, 1.0766272660260501e-23, -2.1584244108805566e-24, -3.457356466530233e-24, -2.8046592644376095e-24, 7.94868869875175e-25, -1.2569267901684678e-24, -1.124448645189272e-24, 2.0097903945624344e-24, 4.9695460238537366e-24, -9.17653492051015e-25, -6.526972020926234e-25, 1.2149215246872594e-24, 2.8822074468644558e-24, -1.0662875083691372e-25, -1.8611563782443123e-24, -1.1813173123022926e-23, -1.5037481145489147e-23, -1.4359338446037715e-23, -9.65474871214237e-24, -1.6285118309637732e-24, -5.428372769879244e-25, -6.371875656072541e-24, -5.2603517079544104e-24, 3.903258515484599e-24, 8.019774532643026e-24, -3.360421238496675e-24, 2.0679515313825692e-25, 5.450990989753741e-24, 8.271806125530277e-25, -1.83530698410203e-24, -1.357093192469811e-24, 0.0, 3.748162150630907e-24, 4.872610795820179e-24, 1.7060600133906196e-24, -3.799860938915471e-24, -1.9516292577422997e-24, -1.0339757656912846e-25, 2.0679515313825692e-24, 1.8611563782443123e-24, 8.271806125530277e-24, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>- Шәңгәрәй эшһеҙ-шөғөлһөҙ ятыуҙан ағарып, нәҙегәйеп ҡалған бармаҡтары менән үңәсен ышҡыны.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>sixties</td>\n",
       "      <td>male_masculine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3024459e489b395b30fe5221c17d7c0c4d287cca2a69df62c78155d6167a423e173bfa262b7e1ce379b6c0a3cbd3b904b25364980cb92b5dbcfee5061f163d5c</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/c2c22acf185d9d78077a9485cc6687145cc56b7e1780652a4e8aa43aff5cd21f/ba_train_1/common_voice_ba_26226950.mp3', 'array': [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>— Үлемде күргәнем бар...</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>thirties</td>\n",
       "      <td>female_feminine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8861729e0f44d9e23ab916bd84784292790a58ce9d7059f6b58f6429815c16e5516a68561a95872da770523482b21141b0a5a384340604ad0f63d8f371de4df7</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/aba413718ed4fe3f7cc687eda89d7f07fad095a757c628c75c723633e666fd56/ba_train_0/common_voice_ba_26258558.mp3', 'array': [4.263256414560601e-14, -1.2079226507921703e-13, 1.7763568394002505e-14, 2.842170943040401e-14, -5.542233338928781e-13, -1.3358203432289883e-12, -2.0179413695586845e-12, -2.3021584638627246e-12, -1.7195134205394424e-12, -1.0516032489249483e-12, -6.536993168992922e-13, -8.810729923425242e-13, -1.2931877790833823e-12, -1.9610979506978765e-12, -1.9610979506978765e-12, -9.947598300641403e-13, 8.810729923425242e-13, 2.0179413695586845e-12, 2.8137492336099967e-12, 3.240074875066057e-12, 2.7995383788947947e-12, 2.1884716261411086e-12, 2.0179413695586845e-12, 1.4779288903810084e-12, 1.5631940186722204e-13, -1.3358203432289883e-12, -2.4655832930875476e-12, -3.588240815588506e-12, -4.675371201301459e-12, -5.9259264162392356e-12, -7.51754214434186e-12, -6.494360604847316e-12, -2.0534685063466895e-12, 4.206412995699793e-12, 9.350742402602918e-12, 1.1141310096718371e-11, 8.469669410260394e-12, 4.803268893738277e-12, 6.707523425575346e-12, 1.6228796084760688e-11, 2.9245939003885724e-11, 3.9193537304527126e-11, 3.929301328753354e-11, 2.744826588241267e-11, 1.0658141036401503e-11, -9.805489753489383e-13, -2.9558577807620168e-12, 5.400124791776761e-13, 1.5774048733874224e-12, -4.526157226791838e-12, -1.3805845355818747e-11, -1.5219825399981346e-11, -4.831690603168681e-13, 2.6005864128819667e-11, 4.7265302782761864e-11, 4.6213699533836916e-11, 1.956834694283316e-11, -1.8317791727895383e-11, -4.249045559845399e-11, -3.171862772433087e-11, 1.3500311979441904e-11, 6.716049938404467e-11, 9.689671287560486e-11, 8.910205906431656e-11, 5.297806637827307e-11, 1.1084466677857563e-11, -1.0544454198679887e-11, 1.6768808563938364e-12, 3.809930149145657e-11, 7.831602033547824e-11, 1.1007728062395472e-10, 1.3307044355315156e-10, 1.4998136066424195e-10, 1.5910472939140163e-10, 1.5052137314341962e-10, 1.1198153515579179e-10, 4.4508396968012676e-11, -2.9956481739645824e-11, -7.315748007385992e-11, -5.0818016461562365e-11, 3.8824055081931874e-11, 1.5234036254696548e-10, 2.233377927041147e-10, 2.0662582755903713e-10, 1.0723510968091432e-10, -1.659827830735594e-11, -8.427036846114788e-11, -5.17843545821961e-11, 5.061906449554954e-11, 1.4171064321999438e-10, 1.4918555280019064e-10, 5.88329385209363e-11, -7.281641956069507e-11, -1.5580781109747477e-10, -1.4165379980113357e-10, -6.110667527536862e-11, 1.0828671292983927e-11, 1.5148771126405336e-11, -4.480682491703192e-11, -9.902123565552756e-11, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>— Һаңғыраулыҡ та барҙыр, юғиһә фиал ығы-зығыһын ишетер инем.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>thirties</td>\n",
       "      <td>female_feminine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>21328583ed4c54d1c02eb9acb67e2480a97a2bc0425a5aa56c8408c6ffc65bd2647b13af168e0f9484a36a69cf256984618b9dab49dac4d08d911617df135a30</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/aba413718ed4fe3f7cc687eda89d7f07fad095a757c628c75c723633e666fd56/ba_train_0/common_voice_ba_26091873.mp3', 'array': [1.0658141036401503e-14, 1.7763568394002505e-14, -1.7763568394002505e-14, -2.842170943040401e-14, -8.881784197001252e-14, -1.971756091734278e-13, -2.984279490192421e-13, -1.6342482922482304e-13, 3.197442310920451e-14, 1.2079226507921703e-13, -1.0658141036401503e-14, -2.2026824808563106e-13, -1.1013412404281553e-13, 2.899902540320909e-13, 5.364597654988756e-13, 3.232969447708456e-13, 3.197442310920451e-14, 1.0658141036401503e-14, 5.329070518200751e-15, -3.7125857943465235e-13, -7.922551503725117e-13, -6.536993168992922e-13, 1.0835776720341528e-13, 5.400124791776761e-13, 0.0, -6.217248937900877e-13, -8.171241461241152e-14, 1.1262102361797588e-12, 1.4450662888521038e-12, 6.181721801112872e-13, -7.105427357601002e-14, -5.3290705182007514e-14, -3.197442310920451e-13, -1.5862866575844237e-12, -2.5863755581667647e-12, -1.588063014423824e-12, 7.638334409421077e-13, 1.4086509736443986e-12, -5.613287612504791e-13, -2.1458390619955026e-12, -4.476419235288631e-13, 3.282707439211663e-12, 5.258016244624741e-12, 3.808509063674137e-12, 1.2541079286165768e-12, 2.1316282072803006e-13, 3.765876499528531e-13, 1.687538997430238e-14, -1.2079226507921703e-12, -2.632560835991171e-12, -3.6841640849161195e-12, -3.112177182629239e-12, -2.2737367544323206e-13, 2.5224267119483557e-12, 1.9610979506978765e-12, -3.019806626980426e-13, 8.952838470577262e-13, 5.9685589803848416e-12, 7.617018127348274e-12, 7.389644451905042e-13, -8.08242361927114e-12, -7.565503779005667e-12, 7.709388682997087e-13, 3.623767952376511e-12, -3.4852121189032914e-12, -7.315037464650231e-12, 1.815436689867056e-12, 1.1496581464598421e-11, 4.533262654149439e-12, -1.0409451078885468e-11, -6.206590796864475e-12, 2.148858868622483e-11, 4.149569576838985e-11, 2.8137492336099967e-11, -1.6413537196058314e-12, -1.1908696251339279e-11, 2.0268231537556858e-12, 1.1610268302320037e-11, 1.5916157281026244e-12, -9.00435281891987e-12, -1.6484591469634324e-12, 9.386269539390923e-12, -7.105427357601002e-15, -2.2637891561316792e-11, -2.7490898446558276e-11, -4.192202140984591e-12, 2.220446049250313e-11, 2.559730205575761e-11, 1.0189182830799837e-11, -2.0037305148434825e-12, -1.4495071809506044e-12, 2.618349981275969e-12, -1.6413537196058314e-12, -1.6218137943724287e-11, -3.108269197582558e-11, -3.000977244482783e-11, -8.903100479074055e-12, 1.1230127938688383e-11, 6.778577699151356e-12, -8.881784197001252e-12, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Ҡатының яман булһа, һарғайып киберһең.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>twenties</td>\n",
       "      <td>female_feminine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>e160b36a4c95f67d0d0f35c1f0e262e3275c4ce49a92410607bd64f89a96ccfce73003ec9b45f94c1eaf91c358b3728ddcbbe62c970c2a729b39eedc5b44d296</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/944fc7c543869badc9d8d8062f5e8e33351fb7826c2bd639f752d45bf1d9f1b9/ba_train_2/common_voice_ba_25876729.mp3', 'array': [-1.990403348955723e-24, 2.68833699079734e-24, -4.1359030627651384e-25, 3.9291079096268815e-24, -3.101927297073854e-25, -4.342698215903395e-24, -2.042102137240287e-24, 1.34416849539867e-24, 1.7512964531396133e-24, 1.809457589959748e-24, 7.237830359838992e-25, -2.0679515313825692e-25, -1.2795450100429647e-24, -3.7223127564886245e-24, -2.3781442610899546e-24, 7.302453845194697e-25, 2.4492300949812304e-24, 4.426708746865812e-25, 1.6414365280349143e-24, -1.5057272087879332e-24, -1.1002148381808825e-24, -3.2440989648564054e-24, 1.34416849539867e-24, 2.235972593307403e-24, 2.1842738050228387e-24, 1.6802106192483375e-24, -2.0808762284537102e-24, -2.055026834311428e-24, -8.077935669463161e-25, -5.62224322594636e-25, -1.6026624368214911e-24, 2.6495628995839168e-24, 1.7642211502107543e-24, -2.9985297205047253e-24, -1.5509636485369269e-24, 2.274746684520826e-24, -2.0679515313825692e-24, -1.2407709188295415e-24, -2.481541837659083e-24, 2.68833699079734e-24, -2.714186384939622e-25, 2.0679515313825692e-25, -4.1359030627651384e-25, -4.963083675318166e-24, -6.462348535570529e-26, 8.271806125530277e-24, 3.308722450212111e-24, 1.2924697071141057e-25, -2.0679515313825692e-24, 3.101927297073854e-25, 4.3943970041879595e-25, -3.2053248736429822e-24, 2.5849394142282115e-25, 3.2570236619275465e-24, 2.3522948669476725e-24, 7.884065213396045e-25, -1.783608195817466e-24, -9.822769774067204e-25, 2.946830932220161e-24, 4.1746771539785615e-24, -2.5849394142282115e-25, -6.898557061721539e-25, -2.0679515313825692e-24, -3.101927297073854e-25, -1.822382287030889e-24, -1.932242212135588e-24, 1.4217166778255163e-25, 2.772347521759757e-24, 2.959755629291302e-24, 2.1196503196671334e-24, 3.1172753748458338e-24, 1.550963648536927e-25, -1.4604907690389395e-24, -1.6349741794993438e-24, -3.360421238496675e-24, -1.770683498746325e-24, 7.754818242684634e-26, 7.754818242684634e-24, 5.906586561511463e-24, -1.0469004627624257e-24, -1.9645539548134407e-24, -1.4411037234322279e-24, 2.5849394142282115e-26, 2.895132143935597e-24, 3.0986961228060685e-24, 8.013312184107456e-25, -7.754818242684634e-25, -8.659547037664508e-25, 1.8611563782443123e-24, 7.237830359838992e-25, -8.271806125530277e-25, 2.5849394142282115e-25, 5.945360652724886e-25, -2.4039936552322367e-24, -2.895132143935597e-24, 1.2407709188295415e-24, -1.2924697071141057e-24, -1.2407709188295415e-24, -3.308722450212111e-24, 0.0, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>- Әптеләхәт күҙҙәрен асты ла түшәмгә ҡарап ята бирҙе.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>sixties</td>\n",
       "      <td>male_masculine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>4b7938fa6ff8aae5574194abc152b8905e72203d160a8920ab44c550eabfd9baae1932cd3170fd503efe5fd16051c568b90f201f290aba4245072e9ab8dd3dc5</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/e024c6558d9897612fd8f5a6b3c29f7c888176fe04022cbd549f5518312bfd53/ba_dev_0/common_voice_ba_26054132.mp3', 'array': [6.815758221109542e-28, -6.058451752097371e-28, -3.0292258760486853e-28, -1.2116903504194741e-27, 1.5146129380243427e-28, -6.310887241768094e-28, -1.2874209973206913e-27, -2.0952145642670074e-27, -7.573064690121713e-28, -7.068193710780266e-28, 6.058451752097371e-28, 1.5146129380243427e-28, -2.0194839173657902e-28, -1.1107161545511846e-27, -1.6408306828597046e-28, -5.679798517591285e-29, -2.4296915880807164e-28, 5.806016262426647e-28, 7.9201634884189585e-28, 6.68954047627418e-28, 2.9030081312133234e-28, 1.3142422680982057e-27, 2.865142807762715e-27, 1.5777218104420236e-27, -2.477023242393977e-28, 1.4956802762990384e-27, 2.5180440094654697e-27, 2.1125695041818696e-27, 7.573064690121713e-28, 2.524354896707238e-29, 3.281661365719409e-28, 7.573064690121713e-28, 6.310887241768094e-28, 6.058451752097371e-28, -1.0097419586828951e-27, 0.0, -1.0097419586828951e-27, -1.4136387421560532e-27, -1.4136387421560532e-27, -1.4136387421560532e-27, -1.8175355256292112e-27, -4.0389678347315804e-28, -2.4233807008389483e-27, -1.6155871338926322e-27, -1.2116903504194741e-27, 2.0194839173657902e-28, -1.2116903504194741e-27, -3.0292258760486853e-28, 3.0292258760486853e-28, -3.0292258760486853e-28, -2.1078363387505435e-27, -1.7039395552773855e-27, -6.437104986603456e-28, 3.34477023813709e-28, -1.1675141397270975e-27, -1.0196027199981578e-27, 2.524354896707238e-29, -2.524354896707238e-28, -7.667727998748235e-28, -4.165185579566942e-28, -7.9201634884189585e-28, -8.456588903969247e-28, -1.6218980211344003e-27, -8.993014319519535e-29, 1.1296488162764889e-27, -3.7865323450608567e-28, -1.606909663935201e-27, 3.7234234726431757e-28, -6.500213859021137e-28, -7.809722961688017e-28, -8.330371159133885e-28, 1.4515040656066617e-28, -3.9758589623138995e-28, -2.0194839173657902e-28, -1.9753077066734136e-27, -1.4136387421560532e-27, -2.865142807762715e-27, -2.328717392212427e-27, -1.2495556738700827e-27, 2.398137151871876e-28, -8.393480031551566e-28, -1.0349855076499675e-27, 5.427363027920561e-28, 6.184669496932733e-28, 1.2116903504194741e-27, -5.301145283085199e-28, 1.539856486991415e-27, 5.806016262426647e-28, 3.9127500898962186e-28, 8.077935669463161e-28, 1.792291976662139e-27, -1.135959703518257e-28, 1.2621774483536189e-27, 1.666074231826777e-27, 1.5651000359584874e-27, 6.058451752097371e-28, 1.7670484276950664e-27, 1.6155871338926322e-27, 1.6155871338926322e-27, 8.077935669463161e-28, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Фәҡирлек ғәйеп түгел, ялҡаулыҡ ғәйеп.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>twenties</td>\n",
       "      <td>male_masculine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8535f9f4ecb07a3756bb1d71743cc8bb29c29fb868c41b32d3d67929aae8f2d34a481cd8340cd267ecd9d156b1473a60ac1d46b8e1e9080b01a09ce6fea8e374</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/c2c22acf185d9d78077a9485cc6687145cc56b7e1780652a4e8aa43aff5cd21f/ba_train_1/common_voice_ba_26190836.mp3', 'array': [1.1368683772161603e-13, 4.149569576838985e-12, 6.707523425575346e-12, 5.059064278611913e-12, 3.694822225952521e-12, 4.547473508864641e-12, 3.751665644813329e-12, 2.7284841053187847e-12, 1.8189894035458565e-12, 7.673861546209082e-13, -8.526512829121202e-13, -9.094947017729282e-13, -1.9042545318370685e-12, -4.263256414560601e-12, -4.888534022029489e-12, -5.7980287238024175e-12, -8.58335624798201e-12, -8.810729923425242e-12, -5.4569682106375694e-12, -6.252776074688882e-13, 5.9117155615240335e-12, 1.2732925824820995e-11, 1.3528733688872308e-11, 8.753886504564434e-12, 1.1368683772161603e-13, -9.094947017729282e-12, -1.7280399333685637e-11, -1.878674993349705e-11, -1.0686562745831907e-11, 3.183231456205249e-12, 1.5802470443304628e-11, 2.3703705664956942e-11, 2.8819613362429664e-11, 3.12070369545836e-11, 2.9331204132176936e-11, 2.2680524125462398e-11, 1.5688783605583012e-11, 1.0913936421275139e-11, 5.7980287238024175e-12, -7.958078640513122e-12, -3.2514435588382185e-11, -5.843503458891064e-11, -6.917844075360335e-11, -7.102585186657961e-11, -8.495248948747758e-11, -1.1465317584224977e-10, -1.4443912732531317e-10, -1.581099695613375e-10, -1.4358647604240105e-10, -9.515588317299262e-11, -1.91562321560923e-11, 6.650680006714538e-11, 1.2937562132719904e-10, 1.2812506611226127e-10, 4.6497916628140956e-11, -7.821654435247183e-11, -1.8451373762218282e-10, -2.276010491186753e-10, -2.0406787371030077e-10, -1.475655153626576e-10, -9.947598300641403e-11, -7.844391802791506e-11, -8.662937034387141e-11, -1.1436895874794573e-10, -1.3147882782504894e-10, -1.1590373105718754e-10, -7.992184691829607e-11, -4.4565240386873484e-11, -2.5920599000528455e-11, -3.956301952712238e-11, -7.742073648842052e-11, -1.007265382213518e-10, -7.707967597525567e-11, 1.8758328224066645e-12, 1.0203393685515039e-10, 1.4983925211708993e-10, 8.799361239653081e-11, -4.922640073345974e-11, -1.7757884052116424e-10, -2.362412487855181e-10, -2.15550244320184e-10, -1.4506440493278205e-10, -8.29913915367797e-11, -8.174083632184193e-11, -1.8309265215066262e-10, -4.0688519220566377e-10, -6.920117812114768e-10, -8.89428974915063e-10, -8.675442586536519e-10, -6.17319528828375e-10, -2.710294211283326e-10, -3.956301952712238e-11, -5.275069270282984e-11, -2.53749021794647e-10, -5.029505700804293e-10, -7.360085874097422e-10, -9.46556610870175e-10, -1.1033307600882836e-09, -1.163925844593905e-09, -1.136641003540717e-09, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Өс-дүрт көндән ярҙам килеп етергә тейеш.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9d5f6665597f4ddc6a310d5323b128cc1336a83a3ae499c21039f1c634bdf6ab06e029e7d7ded7462137a61433af2cbc70d34e5ef86cb0cfc01d08a1588993a1</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/944fc7c543869badc9d8d8062f5e8e33351fb7826c2bd639f752d45bf1d9f1b9/ba_train_2/common_voice_ba_26096270.mp3', 'array': [-3.680953725860973e-23, 1.075334796318936e-23, 2.481541837659083e-23, 4.9217246446905147e-23, 1.3855275260263214e-23, -3.639594695233322e-23, -2.936491174563248e-23, 1.613002194478404e-23, -2.68833699079734e-23, -4.963083675318166e-24, -1.6543612251060553e-23, 3.970466940254533e-23, 1.7887780746459223e-23, -2.150669592637872e-23, -4.880365614062863e-23, -1.34416849539867e-23, 2.2333876538931747e-23, 2.9158116592494226e-23, -9.822769774067204e-25, -1.8301371052735737e-23, -1.5509636485369269e-24, -2.016252743098005e-23, -4.8596860987490376e-23, 3.5361971186641933e-23, 2.3290304122196185e-23, -6.2038545941477076e-24, 1.3648480107124957e-23, -1.7577588016751838e-24, 3.019209235818551e-23, 2.088631046696395e-23, 1.6543612251060553e-24, 2.0679515313825692e-23, -2.4608623223452573e-23, -4.963083675318166e-23, 1.819797347616661e-23, 4.1359030627651384e-24, -1.9852334701272664e-23, 1.6543612251060553e-23, -2.481541837659083e-23, -3.680953725860973e-23, -5.790264287871194e-23, 1.3234889800848443e-23, -2.6469779601696886e-23, -5.293955920339377e-23, 9.926167350636332e-24, 3.970466940254533e-23, -5.955700410381799e-23, -2.285086442177739e-23, -1.3648480107124957e-23, 0.0, 1.406207041340147e-23, -1.111523948118131e-23, 3.4638188150658034e-23, 2.212708138579349e-23, -1.9102702271146483e-23, -2.750375536738817e-23, -2.2023683809224362e-23, 1.760343741089412e-23, 3.474158572722716e-23, 6.162495563520056e-23, 3.618915179919496e-24, 1.8404768629304866e-23, 1.002956492720546e-23, -2.223047896236262e-23, -5.997059441009451e-24, -8.478601278668534e-24, -8.375203702099405e-24, 1.075334796318936e-23, -1.7784383169890095e-23, -2.750375536738817e-23, 2.6056189295420372e-23, 2.90547190159251e-23, -1.2407709188295415e-24, -4.487454823100175e-23, -9.952016744778614e-23, -7.982292911136717e-23, -1.406207041340147e-23, -8.271806125530277e-25, 4.880365614062863e-23, -3.908428394313056e-23, -3.288042934898285e-23, -1.5302841332231012e-23, 1.675040740419881e-23, 6.493367808541267e-23, 3.1846453583291565e-23, 7.651420666115506e-24, -9.512577044359818e-24, -4.1359030627651384e-24, 2.6469779601696886e-23, 2.9778502051908996e-23, -3.970466940254533e-23, -3.308722450212111e-24, 8.271806125530277e-24, 1.9025154088719637e-23, -6.617444900424222e-24, 1.3234889800848443e-23, -5.790264287871194e-24, 3.3087224502121107e-23, 1.3234889800848443e-23, 1.9852334701272664e-23, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Туйығыҙ ҡотло булһын!</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2708e2fb869bc54793cf48dd35de1f5c15a613e160eb915e0d6508145f03d906e467db8b6933ce3e028ee9efc39e5bbf70011ad653be23ad1c483e913a4b3c23</td>\n",
       "      <td>{'path': '/root/.cache/huggingface/datasets/downloads/extracted/aba413718ed4fe3f7cc687eda89d7f07fad095a757c628c75c723633e666fd56/ba_train_0/common_voice_ba_25938224.mp3', 'array': [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...], 'sampling_rate': 48000}</td>\n",
       "      <td>Йәш, һылыу ҡатынын көнләшеү тойғоһо ҡапыл тынын ҡурһа, шаҡшы хистәрҙе үҙенән тиҙерәк ҡыуырға тырышты.</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>twenties</td>\n",
       "      <td>female_feminine</td>\n",
       "      <td></td>\n",
       "      <td>ba</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_random_elements(common_voice_train.remove_columns([\"path\"]), num_examples=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b112f847-595f-48df-a78c-f5c4b2749a91",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "chars_to_remove_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\“\\%\\‘\\”\\�\\'\\«\\»\\–\\—aijno]'\n",
    "\n",
    "def remove_special_characters(batch):\n",
    "    batch[\"sentence\"] = re.sub(chars_to_remove_regex, ' ', batch[\"sentence\"]).lower()\n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d0bc29a2-f32a-4861-80c5-f679ea90251a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2a663afae3b842f1a662fd69dd6f9897",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/133675 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e39a3446f5164e75bea40dd91bea115a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/14513 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "common_voice_train = common_voice_train.map(remove_special_characters)\n",
    "common_voice_test = common_voice_test.map(remove_special_characters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "8a610f62-dc12-4a24-8446-46b98625b130",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "chars_to_remove_regex = {'й':'й','i':''}\n",
    "\n",
    "def replace_bad_characters(batch):\n",
    "    for k in chars_to_remove_regex:\n",
    "        batch[\"sentence\"] = re.sub(k, chars_to_remove_regex[k], batch[\"sentence\"]).lower()\n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "7ee64093-ff2f-4bce-9b64-1e1953c2bfb6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0614406ce2c04c59990e0126c777f5ba",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/133675 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "12f4b755815748e9880b84c9eb6f8a85",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/14513 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "common_voice_train = common_voice_train.map(replace_bad_characters)\n",
    "common_voice_test = common_voice_test.map(replace_bad_characters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "803068fc-563d-48d8-9741-c64675029249",
   "metadata": {},
   "outputs": [],
   "source": [
    "# show_random_elements(common_voice_train.remove_columns([\"path\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "d1f01bdc-8d08-47b4-9aca-4b868bb49617",
   "metadata": {},
   "outputs": [],
   "source": [
    "def replace_hatted_characters(batch):\n",
    "    batch[\"sentence\"] = re.sub('[я]', 'йа', batch[\"sentence\"])\n",
    "    batch[\"sentence\"] = re.sub('[ю]', 'йу', batch[\"sentence\"])\n",
    "    batch[\"sentence\"] = re.sub('[ё]', 'йо', batch[\"sentence\"])\n",
    "    batch[\"sentence\"] = re.sub('[ъ]', '', batch[\"sentence\"])\n",
    "    batch[\"sentence\"] = re.sub('[ь]', '', batch[\"sentence\"])\n",
    "    if 'е' in batch[\"sentence\"]:\n",
    "        words=batch[\"sentence\"].split(' ')\n",
    "        new_list=[]\n",
    "        for word in words:\n",
    "            if len(word)==0:\n",
    "                continue\n",
    "            new_word=word\n",
    "            if word[0]=='е':\n",
    "                new_word='йэ'+word[1:]\n",
    "            new_word=re.sub('[е]', 'э', new_word)\n",
    "            new_list.append(new_word)\n",
    "\n",
    "        batch[\"sentence\"] = \" \".join(new_list)\n",
    "        \n",
    "    words=batch[\"sentence\"].split(' ')\n",
    "    while '' in words:\n",
    "        words.remove('')\n",
    "    \n",
    "    batch[\"sentence\"]=\" \".join(words)\n",
    "    \n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "c014745a-bcb2-44c2-bde0-fc1042eadae5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6809f4cbb1a046faa2bdb1eb1e217095",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/133675 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "43c4854dd9e74bf3b78cbd9cc80988f8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/14513 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "common_voice_train = common_voice_train.map(replace_hatted_characters)\n",
    "common_voice_test = common_voice_test.map(replace_hatted_characters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "7b383e1a-c60f-45af-b8c7-99ade6b22f42",
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_all_chars(batch):\n",
    "    all_text = \" \".join(batch[\"sentence\"])\n",
    "    vocab = list(set(all_text))\n",
    "    return {\"vocab\": [vocab], \"all_text\": [all_text]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ca3faada-7878-43fb-a14f-7aecff6b4454",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['client_id',\n",
       " 'path',\n",
       " 'audio',\n",
       " 'sentence',\n",
       " 'up_votes',\n",
       " 'down_votes',\n",
       " 'age',\n",
       " 'gender',\n",
       " 'accent',\n",
       " 'locale',\n",
       " 'segment',\n",
       " 'variant']"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "common_voice_train.column_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "141b3b35-dcca-4f4e-92f5-625c6ef1c229",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a1cae338090f4d2091fbd06bbb494325",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/133675 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5767fdd10d364312bd0ae89101a86f39",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/14513 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "vocab_train = common_voice_train.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_train.column_names)\n",
    "vocab_test = common_voice_test.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_test.column_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "1009b091-90ea-4219-ad34-42892e385d12",
   "metadata": {},
   "outputs": [],
   "source": [
    "common_voice_train = common_voice_train.cast_column(\"audio\", Audio(sampling_rate=16_000))\n",
    "common_voice_test = common_voice_test.cast_column(\"audio\", Audio(sampling_rate=16_000))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "8568f380-9127-4d3c-a81f-d46676443034",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import IPython.display as ipd\n",
    "# import numpy as np\n",
    "# import random\n",
    "\n",
    "# rand_int = random.randint(0, len(common_voice_train)-1)\n",
    "\n",
    "# print(common_voice_train[rand_int][\"sentence\"])\n",
    "# ipd.Audio(data=common_voice_train[rand_int][\"audio\"][\"array\"], autoplay=True, rate=16000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "12f07b7c-6624-4768-97fc-e0952d537f6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# rand_int = random.randint(0, len(common_voice_train)-1)\n",
    "\n",
    "# print(\"Target text:\", common_voice_train[rand_int][\"sentence\"])\n",
    "# print(\"Input array shape:\", common_voice_train[rand_int][\"audio\"][\"array\"].shape)\n",
    "# print(\"Sampling rate:\", common_voice_train[rand_int][\"audio\"][\"sampling_rate\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b87a5d5-4a44-446e-adcb-d7b7b6300479",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "06bdaa7c-aaab-439d-a877-68c68a58b450",
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab_list = list(set(vocab_train[\"vocab\"][0]) | set(vocab_test[\"vocab\"][0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "3355edc9-52cd-4c46-87f4-3d79934663c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{' ': 0,\n",
       " 'а': 1,\n",
       " 'б': 2,\n",
       " 'в': 3,\n",
       " 'г': 4,\n",
       " 'д': 5,\n",
       " 'ж': 6,\n",
       " 'з': 7,\n",
       " 'и': 8,\n",
       " 'й': 9,\n",
       " 'к': 10,\n",
       " 'л': 11,\n",
       " 'м': 12,\n",
       " 'н': 13,\n",
       " 'о': 14,\n",
       " 'п': 15,\n",
       " 'р': 16,\n",
       " 'с': 17,\n",
       " 'т': 18,\n",
       " 'у': 19,\n",
       " 'ф': 20,\n",
       " 'х': 21,\n",
       " 'ц': 22,\n",
       " 'ч': 23,\n",
       " 'ш': 24,\n",
       " 'щ': 25,\n",
       " 'ы': 26,\n",
       " 'э': 27,\n",
       " 'ғ': 28,\n",
       " 'ҙ': 29,\n",
       " 'ҡ': 30,\n",
       " 'ң': 31,\n",
       " 'ҫ': 32,\n",
       " 'ү': 33,\n",
       " 'һ': 34,\n",
       " 'ә': 35,\n",
       " 'ө': 36}"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vocab_dict = {v: k for k, v in enumerate(sorted(vocab_list))}\n",
    "vocab_dict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "17b7d548-aff0-42a5-8e74-2a4fd4c9ded6",
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab_dict[\"|\"] = vocab_dict[\" \"]\n",
    "del vocab_dict[\" \"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b80e9322-d0c3-4b4f-8ed7-8bd8062d8e89",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "39"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vocab_dict[\"[UNK]\"] = len(vocab_dict)\n",
    "vocab_dict[\"[PAD]\"] = len(vocab_dict)\n",
    "len(vocab_dict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "2e523dfd-43d9-4abf-bf53-dc349809594b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "with open('vocab.json', 'w') as vocab_file:\n",
    "    json.dump(vocab_dict, vocab_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "8ab47fdc-17c1-42f2-b457-5e57225ca0b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c3f88493fe5b4ab28c019fb0ad376a59",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "preprocessor_config.json:   0%|          | 0.00/227 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3d893f722b344b6c95f865b4b5f3f683",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/1.59k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "faf13fdc7f584030984dc2351602d03a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors:   0%|          | 0.00/378M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of HubertForCTC were not initialized from the model checkpoint at utter-project/mHuBERT-147 and are newly initialized: ['encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'encoder.pos_conv_embed.conv.parametrizations.weight.original1', 'lm_head.bias', 'lm_head.weight']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
     ]
    }
   ],
   "source": [
    "model_id = \"utter-project/mHuBERT-147\"\n",
    "feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_id)\n",
    "tokenizer = Wav2Vec2CTCTokenizer(\"vocab.json\", unk_token=\"[UNK]\", pad_token=\"[PAD]\", word_delimiter_token=\"|\")\n",
    "processor = Wav2Vec2Processor(feature_extractor=feature_extractor, tokenizer=tokenizer)\n",
    "\n",
    "model = HubertForCTC.from_pretrained(\n",
    "  model_id,\n",
    "  attention_dropout=0.1,\n",
    "  hidden_dropout=0.1,\n",
    "  feat_proj_dropout=0.1,\n",
    "  mask_time_prob=0.05,\n",
    "  layerdrop=0.1,\n",
    "  final_dropout=0.3,\n",
    "  ctc_loss_reduction=\"mean\",\n",
    "  pad_token_id=processor.tokenizer.pad_token_id,\n",
    "  vocab_size=len(processor.tokenizer),\n",
    ")\n",
    "\n",
    "model.freeze_feature_encoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "1f6d9f67-0c1f-48e0-bc8d-500e1b532cb5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def prepare_dataset(batch):\n",
    "    audio = batch[\"audio\"]\n",
    "\n",
    "    # batched output is \"un-batched\"\n",
    "    batch[\"input_values\"] = processor(audio[\"array\"], sampling_rate=audio[\"sampling_rate\"]).input_values[0]\n",
    "    batch[\"input_length\"] = len(batch[\"input_values\"])\n",
    "    \n",
    "    with processor.as_target_processor():\n",
    "        batch[\"labels\"] = processor(batch[\"sentence\"]).input_ids\n",
    "    return batch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "69f0e285",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0c96ba2bd1894d68aedbf6f16e813c87",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/133675 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "common_voice_train = common_voice_train.map(prepare_dataset, remove_columns=common_voice_train.column_names, num_proc=1)\n",
    "common_voice_test = common_voice_test.map(prepare_dataset, remove_columns=common_voice_test.column_names, num_proc=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "9ba6152c-b553-4e76-9a79-78a997b4d747",
   "metadata": {},
   "outputs": [],
   "source": [
    "# from datasets import Dataset\n",
    "# import pickle\n",
    "# import os\n",
    "\n",
    "# def prepare_item(item):\n",
    "#     try:\n",
    "#         audio = item[\"audio\"]\n",
    "        \n",
    "#         # Process audio\n",
    "#         input_values = processor(audio[\"array\"], sampling_rate=audio[\"sampling_rate\"]).input_values[0]\n",
    "#         input_length = len(input_values)\n",
    "        \n",
    "#         # Process text\n",
    "#         with processor.as_target_processor():\n",
    "#             labels = processor(item[\"sentence\"]).input_ids\n",
    "        \n",
    "#         return {\n",
    "#             \"input_values\": input_values,\n",
    "#             \"input_length\": input_length,\n",
    "#             \"labels\": labels\n",
    "#         }\n",
    "#     except Exception as e:\n",
    "#         print(f\"Error processing item: {e}\")\n",
    "#         return None\n",
    "\n",
    "# def process_dataset(dataset):\n",
    "#     processed_data = []\n",
    "#     ind=0\n",
    "#     for item in dataset:\n",
    "#         ind+=1\n",
    "#         if ind%1000==0:\n",
    "#             print(ind)\n",
    "#         processed_item = prepare_item(item)\n",
    "#         if processed_item is not None:\n",
    "#             processed_data.append(processed_item)\n",
    "    \n",
    "#     return Dataset.from_list(processed_data)\n",
    "\n",
    "# def save_to_pickle(prefix, data, index):\n",
    "#     filename = f\"processed_dataset/{prefix}_{index}.pkl\"\n",
    "#     with open(filename, 'wb') as f:\n",
    "#         pickle.dump(data, f)\n",
    "#     print(f\"Saved {len(data)} items to {filename}\")\n",
    "\n",
    "# def process_dataset(prefix, dataset):\n",
    "#     processed_data = []\n",
    "#     total_processed = 0\n",
    "#     for index, item in enumerate(dataset, start=1):\n",
    "#         if index % 1000 == 0:\n",
    "#             print(f\"Processed {index} items\")\n",
    "        \n",
    "#         processed_item = prepare_item(item)\n",
    "#         if processed_item is not None:\n",
    "#             processed_data.append(processed_item)\n",
    "#             total_processed += 1\n",
    "        \n",
    "#         if len(processed_data) == 1000:\n",
    "#             save_to_pickle(prefix, processed_data, total_processed // 1000)\n",
    "#             processed_data = []  # Clear the list after saving\n",
    "    \n",
    "#     # Save any remaining items\n",
    "#     if processed_data:\n",
    "#         save_to_pickle(prefix, processed_data, (total_processed // 1000) + 1)\n",
    "    \n",
    "#     print(f\"Total processed items: {total_processed}\")\n",
    "#     return total_processed\n",
    "\n",
    "# process_dataset(\"test\", common_voice_test)\n",
    "# process_dataset(\"train\", common_voice_train)\n",
    "# # # Process the dataset\n",
    "# # common_voice_test = process_dataset(common_voice_test)\n",
    "# # common_voice_train = process_dataset(common_voice_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "e6b4d78e-fef4-41d1-89a8-4f4865c8b4f0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# def load_processed_dataset(prefix, directory=\"processed_dataset\"):\n",
    "#     all_data = []\n",
    "#     for filename in sorted(os.listdir(directory)):\n",
    "#         if filename.startswith(f\"{prefix}_\") and filename.endswith(\".pkl\"):\n",
    "#             with open(os.path.join(directory, filename), 'rb') as f:\n",
    "#                 all_data.extend(pickle.load(f))\n",
    "#     return Dataset.from_list(all_data)\n",
    "\n",
    "# # Load test and train datasets\n",
    "# common_voice_test = load_processed_dataset(\"test\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "d80f7401-94d5-4e79-bf48-ee1e42ebf2cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# common_voice_train = load_processed_dataset(\"train\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "555488ff-6018-4b87-9c8f-c4e75a176ce2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "bca44a12-2b91-4b31-a01e-2b1497e7742b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3579461/1950979149.py:1: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate\n",
      "  wer_metric = load_metric(\"wer\", trust_remote_code=True)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1e566bbc4c874932830c571afcf3d0aa",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading builder script:   0%|          | 0.00/1.90k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wer_metric = load_metric(\"wer\", trust_remote_code=True)\n",
    "\n",
    "def compute_metrics(pred):\n",
    "  pred_logits = pred.predictions\n",
    "  pred_ids = np.argmax(pred_logits, axis=-1)\n",
    "  pred.label_ids[pred.label_ids == -100] = processor.tokenizer.pad_token_id\n",
    "  pred_str = processor.batch_decode(pred_ids)\n",
    "  # we do not want to group tokens when computing the metrics\n",
    "  label_str = processor.batch_decode(pred.label_ids, group_tokens=False)\n",
    "  wer = wer_metric.compute(predictions=pred_str, references=label_str)\n",
    "  return {\"wer\": wer}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "28329283-945e-452b-ae92-72d6f884ca82",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.\n"
     ]
    }
   ],
   "source": [
    "data_collator = DataCollatorCTCWithPadding(processor=processor, padding=True)\n",
    "\n",
    "training_args = TrainingArguments(\n",
    "  output_dir=\"training\",\n",
    "  report_to=\"tensorboard\",\n",
    "  per_device_train_batch_size=32,\n",
    "  per_device_eval_batch_size=4,\n",
    "  eval_strategy=\"steps\",\n",
    "  num_train_epochs=60,\n",
    "  fp16=False,\n",
    "  save_steps=1000,\n",
    "  eval_steps=1000,\n",
    "  logging_steps=100,\n",
    "  learning_rate=1e-5,\n",
    "  adam_beta1=0.9,\n",
    "  adam_beta2=0.98,\n",
    "  adam_epsilon=1e-08,\n",
    "  warmup_ratio=0.1,\n",
    "  save_total_limit=5,\n",
    "  push_to_hub=False,\n",
    "  load_best_model_at_end=True,\n",
    ")\n",
    "\n",
    "trainer = Trainer(\n",
    "  model=model,\n",
    "  data_collator=data_collator,\n",
    "  args=training_args,\n",
    "  compute_metrics=compute_metrics,\n",
    "  train_dataset=common_voice_train,\n",
    "  eval_dataset=common_voice_test,\n",
    "  tokenizer=processor.feature_extractor,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86fe9e93-821e-45be-b594-ab34dc7f5ea7",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      \n",
       "      <progress value='246372' max='250680' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      [246372/250680 151:06:36 < 2:38:32, 0.45 it/s, Epoch 58.97/60]\n",
       "    </div>\n",
       "    <table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       " <tr style=\"text-align: left;\">\n",
       "      <th>Step</th>\n",
       "      <th>Training Loss</th>\n",
       "      <th>Validation Loss</th>\n",
       "      <th>Wer</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>1000</td>\n",
       "      <td>51.274600</td>\n",
       "      <td>38.144913</td>\n",
       "      <td>1.003135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2000</td>\n",
       "      <td>31.069500</td>\n",
       "      <td>22.275505</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3000</td>\n",
       "      <td>25.918500</td>\n",
       "      <td>18.995430</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4000</td>\n",
       "      <td>22.799500</td>\n",
       "      <td>16.684248</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5000</td>\n",
       "      <td>18.799000</td>\n",
       "      <td>13.793333</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6000</td>\n",
       "      <td>14.724600</td>\n",
       "      <td>10.601075</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7000</td>\n",
       "      <td>10.061500</td>\n",
       "      <td>7.508481</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8000</td>\n",
       "      <td>6.495400</td>\n",
       "      <td>5.195969</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9000</td>\n",
       "      <td>4.399100</td>\n",
       "      <td>3.936890</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10000</td>\n",
       "      <td>3.546100</td>\n",
       "      <td>3.437078</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11000</td>\n",
       "      <td>3.346800</td>\n",
       "      <td>3.310532</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>12000</td>\n",
       "      <td>3.292700</td>\n",
       "      <td>3.262845</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>13000</td>\n",
       "      <td>3.162800</td>\n",
       "      <td>3.125620</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>14000</td>\n",
       "      <td>2.892200</td>\n",
       "      <td>2.813062</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>15000</td>\n",
       "      <td>2.171000</td>\n",
       "      <td>1.956689</td>\n",
       "      <td>1.017752</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>16000</td>\n",
       "      <td>1.549100</td>\n",
       "      <td>1.263318</td>\n",
       "      <td>0.764204</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>17000</td>\n",
       "      <td>1.119200</td>\n",
       "      <td>0.879032</td>\n",
       "      <td>0.599000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>18000</td>\n",
       "      <td>0.841800</td>\n",
       "      <td>0.625173</td>\n",
       "      <td>0.501725</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>19000</td>\n",
       "      <td>0.680500</td>\n",
       "      <td>0.489723</td>\n",
       "      <td>0.445919</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>20000</td>\n",
       "      <td>0.570300</td>\n",
       "      <td>0.405901</td>\n",
       "      <td>0.404730</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>21000</td>\n",
       "      <td>0.475400</td>\n",
       "      <td>0.356388</td>\n",
       "      <td>0.373732</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>22000</td>\n",
       "      <td>0.444100</td>\n",
       "      <td>0.322066</td>\n",
       "      <td>0.351868</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>23000</td>\n",
       "      <td>0.465500</td>\n",
       "      <td>0.294838</td>\n",
       "      <td>0.330790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>24000</td>\n",
       "      <td>0.369500</td>\n",
       "      <td>0.282053</td>\n",
       "      <td>0.314791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25000</td>\n",
       "      <td>0.355100</td>\n",
       "      <td>0.263510</td>\n",
       "      <td>0.301062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>26000</td>\n",
       "      <td>0.325300</td>\n",
       "      <td>0.250518</td>\n",
       "      <td>0.289096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>27000</td>\n",
       "      <td>0.329800</td>\n",
       "      <td>0.236835</td>\n",
       "      <td>0.275367</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>28000</td>\n",
       "      <td>0.309400</td>\n",
       "      <td>0.229643</td>\n",
       "      <td>0.268569</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>29000</td>\n",
       "      <td>0.305500</td>\n",
       "      <td>0.229560</td>\n",
       "      <td>0.262008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>30000</td>\n",
       "      <td>0.283100</td>\n",
       "      <td>0.212700</td>\n",
       "      <td>0.251458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31000</td>\n",
       "      <td>0.268200</td>\n",
       "      <td>0.214310</td>\n",
       "      <td>0.246469</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>32000</td>\n",
       "      <td>0.263500</td>\n",
       "      <td>0.209061</td>\n",
       "      <td>0.241964</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>33000</td>\n",
       "      <td>0.266900</td>\n",
       "      <td>0.199398</td>\n",
       "      <td>0.236324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>34000</td>\n",
       "      <td>0.262700</td>\n",
       "      <td>0.199029</td>\n",
       "      <td>0.230953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>35000</td>\n",
       "      <td>0.288900</td>\n",
       "      <td>0.194922</td>\n",
       "      <td>0.225909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>36000</td>\n",
       "      <td>0.242100</td>\n",
       "      <td>0.190273</td>\n",
       "      <td>0.219269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>37000</td>\n",
       "      <td>0.228300</td>\n",
       "      <td>0.190511</td>\n",
       "      <td>0.218943</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>38000</td>\n",
       "      <td>0.235500</td>\n",
       "      <td>0.188543</td>\n",
       "      <td>0.215224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>39000</td>\n",
       "      <td>0.245700</td>\n",
       "      <td>0.183256</td>\n",
       "      <td>0.212482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>40000</td>\n",
       "      <td>0.236100</td>\n",
       "      <td>0.179355</td>\n",
       "      <td>0.208011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>41000</td>\n",
       "      <td>0.312700</td>\n",
       "      <td>0.180564</td>\n",
       "      <td>0.206707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>42000</td>\n",
       "      <td>0.213200</td>\n",
       "      <td>0.180565</td>\n",
       "      <td>0.203303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>43000</td>\n",
       "      <td>0.210000</td>\n",
       "      <td>0.175925</td>\n",
       "      <td>0.199011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>44000</td>\n",
       "      <td>0.211800</td>\n",
       "      <td>0.179804</td>\n",
       "      <td>0.200438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>45000</td>\n",
       "      <td>0.199200</td>\n",
       "      <td>0.171060</td>\n",
       "      <td>0.197382</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>46000</td>\n",
       "      <td>0.210100</td>\n",
       "      <td>0.168937</td>\n",
       "      <td>0.194865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>47000</td>\n",
       "      <td>0.209700</td>\n",
       "      <td>0.171020</td>\n",
       "      <td>0.192854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>48000</td>\n",
       "      <td>0.202900</td>\n",
       "      <td>0.167084</td>\n",
       "      <td>0.190147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>49000</td>\n",
       "      <td>0.247000</td>\n",
       "      <td>0.167419</td>\n",
       "      <td>0.188517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>50000</td>\n",
       "      <td>0.193200</td>\n",
       "      <td>0.168526</td>\n",
       "      <td>0.189124</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>51000</td>\n",
       "      <td>0.181300</td>\n",
       "      <td>0.165231</td>\n",
       "      <td>0.184023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>52000</td>\n",
       "      <td>0.193200</td>\n",
       "      <td>0.163603</td>\n",
       "      <td>0.183091</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>53000</td>\n",
       "      <td>0.180100</td>\n",
       "      <td>0.162911</td>\n",
       "      <td>0.181810</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>54000</td>\n",
       "      <td>0.175800</td>\n",
       "      <td>0.163430</td>\n",
       "      <td>0.179889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>55000</td>\n",
       "      <td>0.186500</td>\n",
       "      <td>0.162961</td>\n",
       "      <td>0.178518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>56000</td>\n",
       "      <td>0.182900</td>\n",
       "      <td>0.161885</td>\n",
       "      <td>0.178012</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>57000</td>\n",
       "      <td>0.183100</td>\n",
       "      <td>0.162133</td>\n",
       "      <td>0.177698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>58000</td>\n",
       "      <td>0.178600</td>\n",
       "      <td>0.158952</td>\n",
       "      <td>0.175305</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>59000</td>\n",
       "      <td>0.177000</td>\n",
       "      <td>0.159728</td>\n",
       "      <td>0.174619</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>60000</td>\n",
       "      <td>0.172200</td>\n",
       "      <td>0.156344</td>\n",
       "      <td>0.172327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>61000</td>\n",
       "      <td>0.162100</td>\n",
       "      <td>0.162893</td>\n",
       "      <td>0.171507</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>62000</td>\n",
       "      <td>0.167200</td>\n",
       "      <td>0.156655</td>\n",
       "      <td>0.171384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>63000</td>\n",
       "      <td>0.159300</td>\n",
       "      <td>0.155576</td>\n",
       "      <td>0.167743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>64000</td>\n",
       "      <td>0.173300</td>\n",
       "      <td>0.154201</td>\n",
       "      <td>0.168384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>65000</td>\n",
       "      <td>0.162100</td>\n",
       "      <td>0.155397</td>\n",
       "      <td>0.166901</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>66000</td>\n",
       "      <td>0.166000</td>\n",
       "      <td>0.152455</td>\n",
       "      <td>0.166373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>67000</td>\n",
       "      <td>0.163800</td>\n",
       "      <td>0.154483</td>\n",
       "      <td>0.164721</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>68000</td>\n",
       "      <td>0.158700</td>\n",
       "      <td>0.155835</td>\n",
       "      <td>0.164553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>69000</td>\n",
       "      <td>0.165300</td>\n",
       "      <td>0.150448</td>\n",
       "      <td>0.163069</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>70000</td>\n",
       "      <td>0.155300</td>\n",
       "      <td>0.151192</td>\n",
       "      <td>0.163744</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>71000</td>\n",
       "      <td>0.157500</td>\n",
       "      <td>0.150181</td>\n",
       "      <td>0.161834</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>72000</td>\n",
       "      <td>0.214400</td>\n",
       "      <td>0.149456</td>\n",
       "      <td>0.161384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>73000</td>\n",
       "      <td>0.170000</td>\n",
       "      <td>0.149736</td>\n",
       "      <td>0.161159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>74000</td>\n",
       "      <td>0.160300</td>\n",
       "      <td>0.154106</td>\n",
       "      <td>0.160115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>75000</td>\n",
       "      <td>0.145000</td>\n",
       "      <td>0.150480</td>\n",
       "      <td>0.157800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>76000</td>\n",
       "      <td>0.141900</td>\n",
       "      <td>0.149512</td>\n",
       "      <td>0.157317</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>77000</td>\n",
       "      <td>0.142400</td>\n",
       "      <td>0.151584</td>\n",
       "      <td>0.158193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>78000</td>\n",
       "      <td>0.255900</td>\n",
       "      <td>0.150046</td>\n",
       "      <td>0.157980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>79000</td>\n",
       "      <td>0.159100</td>\n",
       "      <td>0.148835</td>\n",
       "      <td>0.155924</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>80000</td>\n",
       "      <td>0.210400</td>\n",
       "      <td>0.149499</td>\n",
       "      <td>0.156744</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>81000</td>\n",
       "      <td>0.139200</td>\n",
       "      <td>0.148260</td>\n",
       "      <td>0.154519</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>82000</td>\n",
       "      <td>0.147600</td>\n",
       "      <td>0.148945</td>\n",
       "      <td>0.153227</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>83000</td>\n",
       "      <td>0.134800</td>\n",
       "      <td>0.143957</td>\n",
       "      <td>0.152587</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>84000</td>\n",
       "      <td>0.152700</td>\n",
       "      <td>0.147464</td>\n",
       "      <td>0.153014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>85000</td>\n",
       "      <td>0.132300</td>\n",
       "      <td>0.145350</td>\n",
       "      <td>0.150508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>86000</td>\n",
       "      <td>0.143100</td>\n",
       "      <td>0.144224</td>\n",
       "      <td>0.150610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>87000</td>\n",
       "      <td>0.145600</td>\n",
       "      <td>0.143185</td>\n",
       "      <td>0.151115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>88000</td>\n",
       "      <td>0.146500</td>\n",
       "      <td>0.144387</td>\n",
       "      <td>0.149902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>89000</td>\n",
       "      <td>0.135300</td>\n",
       "      <td>0.149918</td>\n",
       "      <td>0.149913</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>90000</td>\n",
       "      <td>0.146800</td>\n",
       "      <td>0.144372</td>\n",
       "      <td>0.148452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>91000</td>\n",
       "      <td>0.137400</td>\n",
       "      <td>0.143531</td>\n",
       "      <td>0.146632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>92000</td>\n",
       "      <td>0.131000</td>\n",
       "      <td>0.146236</td>\n",
       "      <td>0.148362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>93000</td>\n",
       "      <td>0.141100</td>\n",
       "      <td>0.143836</td>\n",
       "      <td>0.147340</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>94000</td>\n",
       "      <td>0.136200</td>\n",
       "      <td>0.144888</td>\n",
       "      <td>0.147610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>95000</td>\n",
       "      <td>0.131900</td>\n",
       "      <td>0.141101</td>\n",
       "      <td>0.146610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>96000</td>\n",
       "      <td>0.130400</td>\n",
       "      <td>0.140892</td>\n",
       "      <td>0.145194</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>97000</td>\n",
       "      <td>0.137600</td>\n",
       "      <td>0.143972</td>\n",
       "      <td>0.146430</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>98000</td>\n",
       "      <td>0.142600</td>\n",
       "      <td>0.142365</td>\n",
       "      <td>0.145846</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>99000</td>\n",
       "      <td>0.125900</td>\n",
       "      <td>0.143896</td>\n",
       "      <td>0.146947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>100000</td>\n",
       "      <td>0.133800</td>\n",
       "      <td>0.142545</td>\n",
       "      <td>0.143700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>101000</td>\n",
       "      <td>0.117900</td>\n",
       "      <td>0.142868</td>\n",
       "      <td>0.144554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>102000</td>\n",
       "      <td>0.221200</td>\n",
       "      <td>0.140761</td>\n",
       "      <td>0.143857</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>103000</td>\n",
       "      <td>0.124800</td>\n",
       "      <td>0.142182</td>\n",
       "      <td>0.143913</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>104000</td>\n",
       "      <td>0.120300</td>\n",
       "      <td>0.142867</td>\n",
       "      <td>0.143632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>105000</td>\n",
       "      <td>0.122200</td>\n",
       "      <td>0.143367</td>\n",
       "      <td>0.142161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>106000</td>\n",
       "      <td>0.163800</td>\n",
       "      <td>0.141867</td>\n",
       "      <td>0.141947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>107000</td>\n",
       "      <td>0.244400</td>\n",
       "      <td>0.138591</td>\n",
       "      <td>0.142408</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>108000</td>\n",
       "      <td>0.122200</td>\n",
       "      <td>0.141987</td>\n",
       "      <td>0.140588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>109000</td>\n",
       "      <td>0.158200</td>\n",
       "      <td>0.140095</td>\n",
       "      <td>0.140408</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>110000</td>\n",
       "      <td>0.117500</td>\n",
       "      <td>0.144389</td>\n",
       "      <td>0.141206</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>111000</td>\n",
       "      <td>0.126300</td>\n",
       "      <td>0.141468</td>\n",
       "      <td>0.141520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>112000</td>\n",
       "      <td>0.125000</td>\n",
       "      <td>0.137573</td>\n",
       "      <td>0.139543</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>113000</td>\n",
       "      <td>0.120900</td>\n",
       "      <td>0.140267</td>\n",
       "      <td>0.140060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>114000</td>\n",
       "      <td>0.124400</td>\n",
       "      <td>0.141699</td>\n",
       "      <td>0.140172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>115000</td>\n",
       "      <td>0.118400</td>\n",
       "      <td>0.140943</td>\n",
       "      <td>0.138992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>116000</td>\n",
       "      <td>0.113800</td>\n",
       "      <td>0.141139</td>\n",
       "      <td>0.137442</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>117000</td>\n",
       "      <td>0.115700</td>\n",
       "      <td>0.138694</td>\n",
       "      <td>0.138060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>118000</td>\n",
       "      <td>0.117500</td>\n",
       "      <td>0.142219</td>\n",
       "      <td>0.139251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>119000</td>\n",
       "      <td>0.115100</td>\n",
       "      <td>0.143673</td>\n",
       "      <td>0.137981</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>120000</td>\n",
       "      <td>0.113000</td>\n",
       "      <td>0.141772</td>\n",
       "      <td>0.137341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>121000</td>\n",
       "      <td>0.120900</td>\n",
       "      <td>0.141847</td>\n",
       "      <td>0.136813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>122000</td>\n",
       "      <td>0.123700</td>\n",
       "      <td>0.137646</td>\n",
       "      <td>0.135329</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>123000</td>\n",
       "      <td>0.111900</td>\n",
       "      <td>0.140896</td>\n",
       "      <td>0.136779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>124000</td>\n",
       "      <td>0.106400</td>\n",
       "      <td>0.141450</td>\n",
       "      <td>0.136431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>125000</td>\n",
       "      <td>0.203500</td>\n",
       "      <td>0.138362</td>\n",
       "      <td>0.134813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>126000</td>\n",
       "      <td>0.117000</td>\n",
       "      <td>0.140300</td>\n",
       "      <td>0.135498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>127000</td>\n",
       "      <td>0.115500</td>\n",
       "      <td>0.142952</td>\n",
       "      <td>0.135790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>128000</td>\n",
       "      <td>0.112600</td>\n",
       "      <td>0.139224</td>\n",
       "      <td>0.134790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>129000</td>\n",
       "      <td>0.130500</td>\n",
       "      <td>0.137822</td>\n",
       "      <td>0.135037</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>130000</td>\n",
       "      <td>0.105700</td>\n",
       "      <td>0.142470</td>\n",
       "      <td>0.133970</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>131000</td>\n",
       "      <td>0.107400</td>\n",
       "      <td>0.141909</td>\n",
       "      <td>0.134779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>132000</td>\n",
       "      <td>0.109700</td>\n",
       "      <td>0.139969</td>\n",
       "      <td>0.133981</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>133000</td>\n",
       "      <td>0.112800</td>\n",
       "      <td>0.140087</td>\n",
       "      <td>0.133745</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>134000</td>\n",
       "      <td>0.112400</td>\n",
       "      <td>0.138360</td>\n",
       "      <td>0.133644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>135000</td>\n",
       "      <td>0.142000</td>\n",
       "      <td>0.140858</td>\n",
       "      <td>0.134577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>136000</td>\n",
       "      <td>0.108800</td>\n",
       "      <td>0.140248</td>\n",
       "      <td>0.132105</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>137000</td>\n",
       "      <td>0.109000</td>\n",
       "      <td>0.141520</td>\n",
       "      <td>0.133026</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>138000</td>\n",
       "      <td>0.099900</td>\n",
       "      <td>0.140755</td>\n",
       "      <td>0.132464</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>139000</td>\n",
       "      <td>0.104200</td>\n",
       "      <td>0.139096</td>\n",
       "      <td>0.133442</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>140000</td>\n",
       "      <td>0.141100</td>\n",
       "      <td>0.140202</td>\n",
       "      <td>0.132420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>141000</td>\n",
       "      <td>0.108600</td>\n",
       "      <td>0.138324</td>\n",
       "      <td>0.131498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>142000</td>\n",
       "      <td>0.102600</td>\n",
       "      <td>0.140081</td>\n",
       "      <td>0.132184</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>143000</td>\n",
       "      <td>0.103500</td>\n",
       "      <td>0.143127</td>\n",
       "      <td>0.131217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>144000</td>\n",
       "      <td>0.104900</td>\n",
       "      <td>0.140858</td>\n",
       "      <td>0.130554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>145000</td>\n",
       "      <td>0.111000</td>\n",
       "      <td>0.140586</td>\n",
       "      <td>0.131172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>146000</td>\n",
       "      <td>0.116100</td>\n",
       "      <td>0.141742</td>\n",
       "      <td>0.130476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>147000</td>\n",
       "      <td>0.100100</td>\n",
       "      <td>0.139187</td>\n",
       "      <td>0.130566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>148000</td>\n",
       "      <td>0.101900</td>\n",
       "      <td>0.138004</td>\n",
       "      <td>0.130172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>149000</td>\n",
       "      <td>0.104600</td>\n",
       "      <td>0.138873</td>\n",
       "      <td>0.130588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>150000</td>\n",
       "      <td>0.105700</td>\n",
       "      <td>0.138554</td>\n",
       "      <td>0.129498</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>151000</td>\n",
       "      <td>0.091100</td>\n",
       "      <td>0.140281</td>\n",
       "      <td>0.129431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>152000</td>\n",
       "      <td>0.102800</td>\n",
       "      <td>0.140711</td>\n",
       "      <td>0.129240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>153000</td>\n",
       "      <td>0.111800</td>\n",
       "      <td>0.140982</td>\n",
       "      <td>0.129678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>154000</td>\n",
       "      <td>0.114400</td>\n",
       "      <td>0.136738</td>\n",
       "      <td>0.128633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>155000</td>\n",
       "      <td>0.134700</td>\n",
       "      <td>0.138643</td>\n",
       "      <td>0.128970</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>156000</td>\n",
       "      <td>0.107300</td>\n",
       "      <td>0.138547</td>\n",
       "      <td>0.128060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>157000</td>\n",
       "      <td>0.103200</td>\n",
       "      <td>0.140463</td>\n",
       "      <td>0.128644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>158000</td>\n",
       "      <td>0.098600</td>\n",
       "      <td>0.137649</td>\n",
       "      <td>0.127937</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>159000</td>\n",
       "      <td>0.122500</td>\n",
       "      <td>0.139453</td>\n",
       "      <td>0.128218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>160000</td>\n",
       "      <td>0.098600</td>\n",
       "      <td>0.139871</td>\n",
       "      <td>0.128757</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>161000</td>\n",
       "      <td>0.100800</td>\n",
       "      <td>0.138031</td>\n",
       "      <td>0.128083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>162000</td>\n",
       "      <td>0.107300</td>\n",
       "      <td>0.136944</td>\n",
       "      <td>0.127611</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>163000</td>\n",
       "      <td>0.099900</td>\n",
       "      <td>0.139494</td>\n",
       "      <td>0.127072</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>164000</td>\n",
       "      <td>0.104400</td>\n",
       "      <td>0.137528</td>\n",
       "      <td>0.126723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>165000</td>\n",
       "      <td>0.103800</td>\n",
       "      <td>0.137721</td>\n",
       "      <td>0.126678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>166000</td>\n",
       "      <td>0.101900</td>\n",
       "      <td>0.141310</td>\n",
       "      <td>0.127060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>167000</td>\n",
       "      <td>0.098600</td>\n",
       "      <td>0.140203</td>\n",
       "      <td>0.126678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>168000</td>\n",
       "      <td>0.126900</td>\n",
       "      <td>0.139529</td>\n",
       "      <td>0.126004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>169000</td>\n",
       "      <td>0.112200</td>\n",
       "      <td>0.140427</td>\n",
       "      <td>0.126678</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>170000</td>\n",
       "      <td>0.101400</td>\n",
       "      <td>0.139196</td>\n",
       "      <td>0.126521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>171000</td>\n",
       "      <td>0.103200</td>\n",
       "      <td>0.140440</td>\n",
       "      <td>0.126386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>172000</td>\n",
       "      <td>0.100200</td>\n",
       "      <td>0.138006</td>\n",
       "      <td>0.125735</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>173000</td>\n",
       "      <td>0.106300</td>\n",
       "      <td>0.139007</td>\n",
       "      <td>0.125555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>174000</td>\n",
       "      <td>0.097400</td>\n",
       "      <td>0.139619</td>\n",
       "      <td>0.125690</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>175000</td>\n",
       "      <td>0.132000</td>\n",
       "      <td>0.136017</td>\n",
       "      <td>0.125162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>176000</td>\n",
       "      <td>0.095600</td>\n",
       "      <td>0.136459</td>\n",
       "      <td>0.124959</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>177000</td>\n",
       "      <td>0.105900</td>\n",
       "      <td>0.137903</td>\n",
       "      <td>0.125690</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>178000</td>\n",
       "      <td>0.093200</td>\n",
       "      <td>0.139604</td>\n",
       "      <td>0.125779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>179000</td>\n",
       "      <td>0.098400</td>\n",
       "      <td>0.136779</td>\n",
       "      <td>0.125049</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>180000</td>\n",
       "      <td>0.092200</td>\n",
       "      <td>0.140259</td>\n",
       "      <td>0.125510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>181000</td>\n",
       "      <td>0.089400</td>\n",
       "      <td>0.138410</td>\n",
       "      <td>0.124656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>182000</td>\n",
       "      <td>0.096900</td>\n",
       "      <td>0.139385</td>\n",
       "      <td>0.126161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>183000</td>\n",
       "      <td>0.103100</td>\n",
       "      <td>0.134198</td>\n",
       "      <td>0.125162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>184000</td>\n",
       "      <td>0.102800</td>\n",
       "      <td>0.138234</td>\n",
       "      <td>0.125150</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>185000</td>\n",
       "      <td>0.107900</td>\n",
       "      <td>0.137457</td>\n",
       "      <td>0.125712</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>186000</td>\n",
       "      <td>0.097000</td>\n",
       "      <td>0.138892</td>\n",
       "      <td>0.124802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>187000</td>\n",
       "      <td>0.091400</td>\n",
       "      <td>0.138046</td>\n",
       "      <td>0.125364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>188000</td>\n",
       "      <td>0.098400</td>\n",
       "      <td>0.136643</td>\n",
       "      <td>0.124173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>189000</td>\n",
       "      <td>0.088600</td>\n",
       "      <td>0.136880</td>\n",
       "      <td>0.124633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>190000</td>\n",
       "      <td>0.092600</td>\n",
       "      <td>0.136922</td>\n",
       "      <td>0.123386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>191000</td>\n",
       "      <td>0.096600</td>\n",
       "      <td>0.138373</td>\n",
       "      <td>0.123521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>192000</td>\n",
       "      <td>0.093100</td>\n",
       "      <td>0.135087</td>\n",
       "      <td>0.123600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>193000</td>\n",
       "      <td>0.106600</td>\n",
       "      <td>0.136268</td>\n",
       "      <td>0.123510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>194000</td>\n",
       "      <td>0.095000</td>\n",
       "      <td>0.134988</td>\n",
       "      <td>0.123083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>195000</td>\n",
       "      <td>0.096100</td>\n",
       "      <td>0.136101</td>\n",
       "      <td>0.123914</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>196000</td>\n",
       "      <td>0.105200</td>\n",
       "      <td>0.135597</td>\n",
       "      <td>0.122746</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>197000</td>\n",
       "      <td>0.097600</td>\n",
       "      <td>0.137379</td>\n",
       "      <td>0.123971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>198000</td>\n",
       "      <td>0.096200</td>\n",
       "      <td>0.136110</td>\n",
       "      <td>0.123162</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>199000</td>\n",
       "      <td>0.106700</td>\n",
       "      <td>0.135890</td>\n",
       "      <td>0.122892</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>200000</td>\n",
       "      <td>0.094300</td>\n",
       "      <td>0.133059</td>\n",
       "      <td>0.122330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>201000</td>\n",
       "      <td>0.090500</td>\n",
       "      <td>0.136487</td>\n",
       "      <td>0.123420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>202000</td>\n",
       "      <td>0.131900</td>\n",
       "      <td>0.137081</td>\n",
       "      <td>0.123802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>203000</td>\n",
       "      <td>0.102600</td>\n",
       "      <td>0.137688</td>\n",
       "      <td>0.123746</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>204000</td>\n",
       "      <td>0.098000</td>\n",
       "      <td>0.139055</td>\n",
       "      <td>0.123027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>205000</td>\n",
       "      <td>0.098200</td>\n",
       "      <td>0.137493</td>\n",
       "      <td>0.122645</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>206000</td>\n",
       "      <td>0.095700</td>\n",
       "      <td>0.138000</td>\n",
       "      <td>0.123195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>207000</td>\n",
       "      <td>0.094500</td>\n",
       "      <td>0.137277</td>\n",
       "      <td>0.122645</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>208000</td>\n",
       "      <td>0.095200</td>\n",
       "      <td>0.136467</td>\n",
       "      <td>0.122319</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>209000</td>\n",
       "      <td>0.103800</td>\n",
       "      <td>0.136650</td>\n",
       "      <td>0.122634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>210000</td>\n",
       "      <td>0.092100</td>\n",
       "      <td>0.135671</td>\n",
       "      <td>0.121589</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>211000</td>\n",
       "      <td>0.089200</td>\n",
       "      <td>0.135571</td>\n",
       "      <td>0.122207</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>212000</td>\n",
       "      <td>0.089200</td>\n",
       "      <td>0.137377</td>\n",
       "      <td>0.122252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>213000</td>\n",
       "      <td>0.218500</td>\n",
       "      <td>0.137072</td>\n",
       "      <td>0.122634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>214000</td>\n",
       "      <td>0.093800</td>\n",
       "      <td>0.138514</td>\n",
       "      <td>0.122252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>215000</td>\n",
       "      <td>0.092500</td>\n",
       "      <td>0.137538</td>\n",
       "      <td>0.122555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>216000</td>\n",
       "      <td>0.093900</td>\n",
       "      <td>0.136874</td>\n",
       "      <td>0.122083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>217000</td>\n",
       "      <td>0.095600</td>\n",
       "      <td>0.137048</td>\n",
       "      <td>0.122004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>218000</td>\n",
       "      <td>0.091600</td>\n",
       "      <td>0.137705</td>\n",
       "      <td>0.121667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>219000</td>\n",
       "      <td>0.095400</td>\n",
       "      <td>0.137685</td>\n",
       "      <td>0.122184</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>220000</td>\n",
       "      <td>0.092600</td>\n",
       "      <td>0.137937</td>\n",
       "      <td>0.121701</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>221000</td>\n",
       "      <td>0.088700</td>\n",
       "      <td>0.137358</td>\n",
       "      <td>0.121319</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>222000</td>\n",
       "      <td>0.092800</td>\n",
       "      <td>0.137370</td>\n",
       "      <td>0.121532</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>223000</td>\n",
       "      <td>0.080900</td>\n",
       "      <td>0.137575</td>\n",
       "      <td>0.121308</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>224000</td>\n",
       "      <td>0.095700</td>\n",
       "      <td>0.137568</td>\n",
       "      <td>0.120544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>225000</td>\n",
       "      <td>0.082900</td>\n",
       "      <td>0.137623</td>\n",
       "      <td>0.121094</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>226000</td>\n",
       "      <td>0.088500</td>\n",
       "      <td>0.137465</td>\n",
       "      <td>0.121016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>227000</td>\n",
       "      <td>0.096200</td>\n",
       "      <td>0.137685</td>\n",
       "      <td>0.120577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>228000</td>\n",
       "      <td>0.092000</td>\n",
       "      <td>0.136249</td>\n",
       "      <td>0.120431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>229000</td>\n",
       "      <td>0.082900</td>\n",
       "      <td>0.138242</td>\n",
       "      <td>0.120858</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>230000</td>\n",
       "      <td>0.089100</td>\n",
       "      <td>0.137948</td>\n",
       "      <td>0.121274</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>231000</td>\n",
       "      <td>0.086800</td>\n",
       "      <td>0.138300</td>\n",
       "      <td>0.121521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>232000</td>\n",
       "      <td>0.082500</td>\n",
       "      <td>0.137398</td>\n",
       "      <td>0.120712</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>233000</td>\n",
       "      <td>0.085000</td>\n",
       "      <td>0.138532</td>\n",
       "      <td>0.121274</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>234000</td>\n",
       "      <td>0.110700</td>\n",
       "      <td>0.137165</td>\n",
       "      <td>0.120634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>235000</td>\n",
       "      <td>0.084800</td>\n",
       "      <td>0.138183</td>\n",
       "      <td>0.120780</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>236000</td>\n",
       "      <td>0.084200</td>\n",
       "      <td>0.137210</td>\n",
       "      <td>0.120386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>237000</td>\n",
       "      <td>0.124900</td>\n",
       "      <td>0.136396</td>\n",
       "      <td>0.120813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>238000</td>\n",
       "      <td>0.087300</td>\n",
       "      <td>0.137456</td>\n",
       "      <td>0.120364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>239000</td>\n",
       "      <td>0.085400</td>\n",
       "      <td>0.137742</td>\n",
       "      <td>0.120319</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>240000</td>\n",
       "      <td>0.089200</td>\n",
       "      <td>0.137301</td>\n",
       "      <td>0.120106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>241000</td>\n",
       "      <td>0.084100</td>\n",
       "      <td>0.137491</td>\n",
       "      <td>0.120375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>242000</td>\n",
       "      <td>0.093000</td>\n",
       "      <td>0.137459</td>\n",
       "      <td>0.120431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>243000</td>\n",
       "      <td>0.087500</td>\n",
       "      <td>0.136750</td>\n",
       "      <td>0.119881</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>244000</td>\n",
       "      <td>0.090900</td>\n",
       "      <td>0.137386</td>\n",
       "      <td>0.120184</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>245000</td>\n",
       "      <td>0.091800</td>\n",
       "      <td>0.137490</td>\n",
       "      <td>0.120510</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>246000</td>\n",
       "      <td>0.099200</td>\n",
       "      <td>0.136867</td>\n",
       "      <td>0.120184</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><p>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "/root/audio/mhubert/venv/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.\n",
      "  warnings.warn(\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n",
      "IOPub message rate exceeded.\n",
      "The notebook server will temporarily stop sending output\n",
      "to the client in order to avoid crashing it.\n",
      "To change this limit, set the config variable\n",
      "`--NotebookApp.iopub_msg_rate_limit`.\n",
      "\n",
      "Current values:\n",
      "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n",
      "NotebookApp.rate_limit_window=3.0 (secs)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "trainer.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "7774bede-d68e-49d2-b4b4-6bd527b4fd5d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a0944d4ceb7849ae8ad34482e86499f2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "events.out.tfevents.1720638005.sciencebrick.3579461.1:   0%|          | 0.00/625k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "02b064e159d44673a9e6acd224baf9c1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "events.out.tfevents.1720637180.sciencebrick.3579461.0:   0%|          | 0.00/6.25k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3053e555d59e4c8fac616965aeb66b16",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors:   0%|          | 0.00/378M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6e035f42d9ba46f6bbca90ecc2180f93",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "training_args.bin:   0%|          | 0.00/5.11k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4d09b11f2a5e48838c6bcefb08a520ca",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Upload 4 LFS files:   0%|          | 0/4 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/AigizK/training/commit/9515ed057312efdbd933737b5bb3d04ab16a7a69', commit_message='End of training', commit_description='', oid='9515ed057312efdbd933737b5bb3d04ab16a7a69', pr_url=None, pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainer.push_to_hub()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "c1921c49",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1a6d5436f7bf493ab7ee19b74b65cf07",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/17.7k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/AigizK/mHuBERT-147-bashkort/commit/e6f2ad28f7a01efaea1dbd21697268fea5771e32', commit_message='Upload tokenizer', commit_description='', oid='e6f2ad28f7a01efaea1dbd21697268fea5771e32', pr_url=None, pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.push_to_hub(\"AigizK/mHuBERT-147-bashkort\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mhubert",
   "language": "python",
   "name": "mhubert"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}