Whisper Base Bengali
This model is a fine-tuned version of arun100/whisper-base-bn on the mozilla-foundation/common_voice_16_0 bn dataset. It achieves the following results on the evaluation set:
- Loss: 0.2671
- Wer: 35.6026
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-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2423 | 1.72 | 500 | 0.2710 | 35.9570 |
| 0.2329 | 3.43 | 1000 | 0.2671 | 35.6026 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0