Whisper small Ps Kissan - ZFA
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: 0.7433
- Wer: 30.3528
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- 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: 200
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 6.5246 | 300 | 0.5865 | 35.3406 |
| 4.0086 | 13.0437 | 600 | 0.6471 | 32.9684 |
| 4.0086 | 19.5683 | 900 | 0.6991 | 30.9611 |
| 0.0379 | 26.0874 | 1200 | 0.7353 | 30.1095 |
| 0.0008 | 32.6120 | 1500 | 0.7433 | 30.3528 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2