README.md

metadata

language:
  - fr
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
base_model: openai/whisper-small
datasets:
  - mozilla-foundation/common_voice_17_0
  - google/fleurs
  - facebook/multilingual_librispeech
  - facebook/voxpopuli
metrics:
  - wer
model-index:
  - name: Whisper Small Mixed-French
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_17_0 fr
          type: mozilla-foundation/common_voice_17_0
          config: fr
          split: test
          args: fr
        metrics:
          - type: wer
            value: 15.015790814663829
            name: Wer
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: fr_fr
          split: test
        metrics:
          - type: wer
            value: 12.02
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/multilingual_librispeech
          type: facebook/multilingual_librispeech
          config: french
          split: test
        metrics:
          - type: wer
            value: 10.01
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: facebook/voxpopuli
          type: facebook/voxpopuli
          config: fr
          split: test
        metrics:
          - type: wer
            value: 12.23
            name: WER
pipeline_tag: automatic-speech-recognition

Whisper Small Mixed-French

This model is a fine-tuned version of openai/whisper-small on the fr datasets:

• mozilla-foundation/common_voice_17_0
• google/fleurs
• facebook/multilingual_librispeech
• facebook/voxpopuli

It achieves the following results on the evaluation set:

• Loss: 0.3092
• Wer: 15.0158

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: 64
• 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.187	0.2	1000	0.3653	17.3498
0.1445	0.4	2000	0.3379	16.0480
0.1659	0.6	3000	0.3255	15.3772
0.1594	0.8	4000	0.3136	15.1959
0.1371	1.0	5000	0.3092	15.0158

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1