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_0FR (with normalization): 15.38 % - WER on
facebook/voxpopuliFR (with normalization): 16.29 % - WER on
google/fleursfr_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
- Downloads last month
- 32
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for qanastek/whisper-small-french-uncased
Dataset used to train qanastek/whisper-small-french-uncased
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 frtest set self-reported15.380
- Wer on facebook/voxpopuli frtest set self-reported16.290
- Wer on google/fleurs fr_frtest set self-reported13.980