Whisper small Hi - CKS 1311 iiitb
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1203
- Wer: 10.8852
- Cer: 3.4179
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: 1.75e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.0291 | 8.77 | 500 | 0.1099 | 14.2344 | 4.1970 |
| 0.004 | 17.54 | 1000 | 0.1114 | 10.8852 | 3.4682 |
| 0.0001 | 26.32 | 1500 | 0.1185 | 10.7656 | 3.3677 |
| 0.0 | 35.09 | 2000 | 0.1203 | 10.8852 | 3.4179 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7