whisper-small-transcripro_c
This model is a fine-tuned version of ZeroHer0/whisper-small-transcripro_c on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1809
- Wer: 67.3159
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
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0159 | 0.4831 | 200 | 1.1499 | 63.2380 |
| 0.0101 | 0.9662 | 400 | 1.1846 | 65.3074 |
| 0.0057 | 1.4493 | 600 | 1.1855 | 67.0116 |
| 0.0063 | 1.9324 | 800 | 1.1855 | 67.7419 |
| 0.0005 | 2.4155 | 1000 | 1.1809 | 67.3159 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3