Whisper Small finetuned on Bengali
This model is a fine-tuned version of openai/whisper-small on the Common Voice 15 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2886
- Wer Ortho: 66.3996
- Wer: 33.6867
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.5075 | 0.8 | 100 | 0.4573 | 77.5920 | 45.3485 |
| 0.257 | 1.6 | 200 | 0.2886 | 66.3996 | 33.6867 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Shamik/whisper-small-bn
Base model
openai/whisper-smallDataset used to train Shamik/whisper-small-bn
Space using Shamik/whisper-small-bn 1
Evaluation results
- Wer on Common Voice 15validation set self-reported33.687