Whisper Small Hi - Vyapar V5
This model is a fine-tuned version of openai/whisper-small on the Vyapar Calling Data 5 calls manual data dataset. It achieves the following results on the evaluation set:
- Loss: 2.1062
- Wer: 61.9102
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0024 | 31.2540 | 1000 | 1.9432 | 71.9217 |
| 0.0001 | 62.5079 | 2000 | 2.0505 | 62.6007 |
| 0.0001 | 93.7619 | 3000 | 2.0913 | 61.6801 |
| 0.0001 | 125.0 | 4000 | 2.1062 | 61.9102 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0