metadata

library_name: transformers
language:
  - fr
license: mit
base_model: bofenghuang/whisper-large-v3-french
tags:
  - generated_from_trainer
datasets:
  - PraxySante/PxCorpus-PxSLU
metrics:
  - wer
model-index:
  - name: Whisper Large v3 French PxCorpus - Fine-tuning test
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PxCorpus PxSLU
          type: PraxySante/PxCorpus-PxSLU
          args: 'config: fr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 4.112554112554113

Whisper Large v3 French PxCorpus - Fine-tuning test

This model is a fine-tuned version of bofenghuang/whisper-large-v3-french on the PxCorpus PxSLU dataset. It achieves the following results on the evaluation set:

Loss: 0.1903
Wer: 4.1126

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: 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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0016	8.1967	1000	0.1864	5.1948
0.0003	16.3934	2000	0.1773	5.1948
0.0001	24.5902	3000	0.1860	4.1126
0.0	32.7869	4000	0.1903	4.1126

Framework versions

Transformers 4.44.1
Pytorch 2.4.0+cu124
Datasets 2.21.0
Tokenizers 0.19.1