Whisper Small MR v3 - Viraj Patil
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4696
- Wer: 43.2485
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.0966 | 4.0 | 1000 | 0.2840 | 45.4146 |
| 0.007 | 8.0 | 2000 | 0.3871 | 44.2482 |
| 0.0005 | 12.0 | 3000 | 0.4502 | 43.2618 |
| 0.0002 | 16.0 | 4000 | 0.4696 | 43.2485 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.1.2
- Datasets 2.21.0
- Tokenizers 0.19.1