README.md

metadata

language:
  - fr
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
  - hf-asr-leaderboard
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small French
    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: 15.38
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: facebook/voxpopuli fr
          type: facebook/voxpopuli
          config: fr
          split: test
          args: fr
        metrics:
          - name: Wer
            type: wer
            value: 16.29
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs fr_fr
          type: google/fleurs
          config: fr_fr
          split: test
          args: fr_fr
        metrics:
          - name: Wer
            type: wer
            value: 13.98

Whisper Small French

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 fr dataset. It achieves the following results on the evaluation set:

• Loss: 0.00
• WER on mozilla-foundation/common_voice_11_0 FR (with normalization): 15.38 %
• WER on facebook/voxpopuli FR (with normalization): 16.29 %
• WER on google/fleurs fr_fr (with normalization): 13.98 %

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: 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: 5000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.11.0+cu102
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2