whisper-small-kannada-transcribe
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: 0.3186
- Wer: 46.5829
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: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch 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
- training_steps: 5240
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1472 | 2.8517 | 750 | 0.1579 | 50.4750 |
| 0.0637 | 5.7034 | 1500 | 0.1520 | 46.9813 |
| 0.0185 | 8.5551 | 2250 | 0.2074 | 48.2991 |
| 0.0043 | 11.4068 | 3000 | 0.2651 | 46.5216 |
| 0.0013 | 14.2586 | 3750 | 0.2989 | 47.0120 |
| 0.0005 | 17.1103 | 4500 | 0.3186 | 46.5829 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 7
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 shadabsayd/whisper-small-kannada-transcribe
Base model
openai/whisper-small