Downloads · 30 days
4
8% of all-time downloads
whisper-small-fr
mahimairaja/whisper-small-fr
whisper-small-fr is a automatic speech recognition model from mahimairaja. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
242M
967 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- e90bc1d1
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
whisper-small-fr
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2859
- Wer: 0.2942
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.8374 | 0.2 | 50 | 1.0818 | 0.2837 |
| 1.8054 | 0.4 | 100 | 0.5724 | 0.7520 |
| 0.9168 | 0.6 | 150 | 0.4289 | 0.7111 |
| 0.7397 | 0.8 | 200 | 0.3737 | 0.4067 |
| 0.6221 | 1.0 | 250 | 0.3158 | 0.3164 |
| 0.3872 | 1.2 | 300 | 0.2803 | 0.2708 |
| 0.3279 | 1.4 | 350 | 0.2731 | 0.2970 |
| 0.3165 | 1.6 | 400 | 0.2779 | 0.3239 |
| 0.3541 | 1.8 | 450 | 0.2832 | 0.4001 |
| 0.2958 | 2.0 | 500 | 0.2790 | 0.2747 |
| 0.1770 | 2.2 | 550 | 0.2926 | 0.4249 |
| 0.1464 | 2.4 | 600 | 0.2901 | 0.3796 |
| 0.1497 | 2.6 | 650 | 0.2863 | 0.2873 |
| 0.1377 | 2.8 | 700 | 0.2862 | 0.2853 |
| 0.1572 | 3.0 | 750 | 0.2859 | 0.2942 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026