<!-- 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-fa_v01
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 fa dataset. It achieves the following results on the evaluation set:
- Loss: 0.2507
- Wer: 30.68
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
You can Find the notebooks here.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- 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
| Step | Training Loss | Validation Loss | Wer |
|---|---|---|---|
| 500 | 1.179600 | 0.504016 | 57.71505 |
| 1000 | 0.341200 | 0.414977 | 45.90970 |
| 1500 | 0.269900 | 0.378401 | 41.06145 |
| 2000 | 0.252000 | 0.342005 | 39.63213 |
| 2500 | 0.222900 | 0.313812 | 37.45793 |
| 3000 | 0.201100 | 0.300456 | 34.49312 |
| 3500 | 0.191800 | 0.276289 | 32.46104 |
| 4000 | 0.173200 | 0.262007 | 31.85010 |
| 4500 | 0.163400 | 0.254489 | 31.00068 |
| 5000 | 0.161000 | 0.250763 | 30.68868 |
Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.3
