whisper-small-bengali-15DB-3e6
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3017
- Wer: 71.9580
- Cer: 26.9873
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: 3e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 4.0799 | 1.2675 | 100 | 0.9942 | 98.0852 | 57.6877 |
| 2.3123 | 2.5350 | 200 | 0.5893 | 82.0259 | 34.1115 |
| 1.7020 | 3.8025 | 300 | 0.4698 | 78.3817 | 30.2375 |
| 1.1852 | 5.0637 | 400 | 0.3643 | 74.1198 | 28.8589 |
| 0.8702 | 6.3312 | 500 | 0.3100 | 72.9463 | 28.0338 |
| 0.7497 | 7.5987 | 600 | 0.3049 | 71.8962 | 27.2188 |
| 0.6472 | 8.8662 | 700 | 0.3017 | 71.9580 | 26.9873 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2