End of training

README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+base_model: openai/whisper-tiny
+tags:
+- generated_from_trainer
+datasets:
+- PolyAI/minds14
+metrics:
+- wer
+model-index:
+- name: whisper-tiny-us-ZA
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: PolyAI/minds14
+      type: PolyAI/minds14
+      config: en-US
+      split: train
+      args: en-US
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.27835051546391754
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/soundofai/huggingface-audio-course-unit5-handson-af/runs/ym0ygfa9)
+# whisper-tiny-us-ZA
+
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6915
+- Wer Ortho: 0.2821
+- Wer: 0.2784
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 5
+- training_steps: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
+| 0.3413        | 3.125  | 100  | 0.4281          | 0.2727    | 0.2474 |
+| 0.0659        | 6.25   | 200  | 0.4672          | 0.2754    | 0.2526 |
+| 0.0076        | 9.375  | 300  | 0.5252          | 0.3035    | 0.2899 |
+| 0.0019        | 12.5   | 400  | 0.5568          | 0.2874    | 0.2758 |
+| 0.0009        | 15.625 | 500  | 0.5804          | 0.2901    | 0.2771 |
+| 0.0006        | 18.75  | 600  | 0.5947          | 0.2861    | 0.2732 |
+| 0.0005        | 21.875 | 700  | 0.6062          | 0.2848    | 0.2745 |
+| 0.0004        | 25.0   | 800  | 0.6170          | 0.2834    | 0.2745 |
+| 0.0003        | 28.125 | 900  | 0.6261          | 0.2834    | 0.2745 |
+| 0.0003        | 31.25  | 1000 | 0.6346          | 0.2781    | 0.2719 |
+| 0.0002        | 34.375 | 1100 | 0.6423          | 0.2794    | 0.2732 |
+| 0.0002        | 37.5   | 1200 | 0.6497          | 0.2794    | 0.2732 |
+| 0.0002        | 40.625 | 1300 | 0.6563          | 0.2794    | 0.2732 |
+| 0.0002        | 43.75  | 1400 | 0.6627          | 0.2794    | 0.2732 |
+| 0.0001        | 46.875 | 1500 | 0.6680          | 0.2941    | 0.2874 |
+| 0.0001        | 50.0   | 1600 | 0.6736          | 0.2874    | 0.2809 |
+| 0.0001        | 53.125 | 1700 | 0.6781          | 0.2874    | 0.2809 |
+| 0.0001        | 56.25  | 1800 | 0.6833          | 0.2874    | 0.2809 |
+| 0.0001        | 59.375 | 1900 | 0.6876          | 0.2834    | 0.2796 |
+| 0.0001        | 62.5   | 2000 | 0.6915          | 0.2821    | 0.2784 |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,248 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.41.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d807e673793a3e4b0addebe209a2e1298d345b58be15a41ce4c1d6a690c7b3
+oid sha256:00eada48b850777220810c22141a6e2b5f7d465488ee9244b1b0938321816bf9
 size 151061672