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
- Downloads last month
- 17
Unable to determine this model's library. Check the
docs
.
Model tree for deepdml/whisper-small-mix-fr
Base model
openai/whisper-smallDatasets used to train deepdml/whisper-small-mix-fr
Evaluation results
- Wer on mozilla-foundation/common_voice_17_0 frtest set self-reported15.016
- WER on google/fleurstest set self-reported12.020
- WER on facebook/multilingual_librispeechtest set self-reported10.010
- WER on facebook/voxpopulitest set self-reported12.230