README.md

metadata

language:
  - cs
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
  - robust-speech-event
  - xlsr-fine-tuning-week
datasets:
  - common_voice
  - ovm
  - pscr
  - vystadial2016
model-index:
  - name: Czech comodoro Wav2Vec2 XLSR 300M 250h data
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 8
          type: mozilla-foundation/common_voice_8_0
          args: cs
        metrics:
          - name: Test WER
            type: wer
            value: 10
          - name: Test CER
            type: cer
            value: 2.6

Czech wav2vec2-xls-r-300m-cs-250

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice 8.0 dataset as well as other datasets listed below.

It achieves the following results on the evaluation set:

• eval_loss: 0.1304
• eval_wer: 0.1517
• eval_cer: 0.0326
• eval_runtime: 358.9895
• eval_samples_per_second: 20.243
• eval_steps_per_second: 2.532
• epoch: 3.13
• step: 31200

The eval.py script results using a LM are: WER: 0.10053685691079459 CER: 0.025859623842234124

Model description

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Czech using the Common Voice dataset. When using this model, make sure that your speech input is sampled at 16kHz.

The model can be used directly (without a language model) as follows:

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "cs", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("comodoro/wav2vec2-xls-r-300m-cs-250")
model = Wav2Vec2ForCTC.from_pretrained("comodoro/wav2vec2-xls-r-300m-cs-250")

resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset[:2]["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits

predicted_ids = torch.argmax(logits, dim=-1)

print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset[:2]["sentence"])

Evaluation

The model can be evaluated using the attached eval.py script:

python eval.py --model_id comodoro/wav2vec2-xls-r-300m-cs-250 --dataset mozilla-foundation/common-voice_8_0 --split test --config cs

Training and evaluation data

The Common Voice 8.0 train and validation datasets were used for training, as well as the following datasets:

• Šmídl, Luboš and Pražák, Aleš, 2013, OVM – Otázky Václava Moravce, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11858/00-097C-0000-000D-EC98-3.

• Pražák, Aleš and Šmídl, Luboš, 2012, Czech Parliament Meetings, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11858/00-097C-0000-0005-CF9C-4.

• Plátek, Ondřej; Dušek, Ondřej and Jurčíček, Filip, 2016, Vystadial 2016 – Czech data, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11234/1-1740.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 600
• num_epochs: 50
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.1+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0