deepdml's picture
Update README.md
3031cda
|
raw
history blame
4.27 kB
metadata
language:
  - fr
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: deepdml/whisper-medium-mix-fr
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 fr
          type: mozilla-foundation/common_voice_11_0
          config: fr
          split: test
          args: fr
        metrics:
          - name: Wer
            type: wer
            value: 11.227820307400155
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: FLEURS ASR
          type: google/fleurs
          config: fr_fr
          split: test
          args: fr
        metrics:
          - name: WER
            type: wer
            value: 9.3526
          - name: Cer
            type: cer
            value: 4.144
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Multilingual LibriSpeech
          type: facebook/multilingual_librispeech
          config: french
          split: test
          args:
            language: fr
        metrics:
          - name: WER
            type: wer
            value: 6.3468
          - name: Cer
            type: cer
            value: 3.1561
      - task:
          type: Automatic Speech Recognition
          name: speech-recognition
        dataset:
          name: VoxPopuli
          type: facebook/voxpopuli
          config: fr
          split: test
          args:
            language: fr
        metrics:
          - name: WER
            type: wer
            value: 10.0653
          - name: Cer
            type: cer
            value: 6.5456

deepdml/whisper-medium-mix-fr

This model is a fine-tuned version of deepdml/whisper-medium-mix-fr on the mozilla-foundation/common_voice_11_0, google/fleurs, facebook/multilingual_librispeech and facebook/voxpopuli datasets. It achieves the following results on the evaluation set:

  • Loss: 0.2599
  • Wer: 11.2278

Using the evalutaion script provided in the Whisper Sprint the model achieves these results on the test sets (WER):

  • google/fleurs: 9.3526 %
    (python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="google/fleurs" --config="fr_fr" --device=0 --language="fr")
  • facebook/multilingual_librispeech: 6.3468 %
    (python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="facebook/multilingual_librispeech" --config="french" --device=0 --language="fr")
  • facebook/voxpopuli: 10.0653 %
    (python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="facebook/voxpopuli" --config="fr" --device=0 --language="fr")

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Training data used: - mozilla-foundation/common_voice_11_0: fr, train+validation - google/fleurs: fr_fr, train - facebook/multilingual_librispeech: french, train - facebook/voxpopuli: fr, train

Evaluating over test split from mozilla-foundation/common_voice_11_0 dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0855 0.25 1000 0.2826 12.4230
0.0569 0.5 2000 0.2768 11.9577
0.0724 0.75 3000 0.2670 11.6106
0.069 1.0 4000 0.2599 11.2278

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2