whisper-hindi-base-2
This model is a fine-tuned version of TheAIchemist13/whisper-hindi-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4431
- Wer: 45.1568
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2311 | 0.42 | 250 | 0.4786 | 50.4530 |
| 0.2449 | 0.84 | 500 | 0.4508 | 49.7561 |
| 0.1269 | 1.26 | 750 | 0.4437 | 45.9233 |
| 0.1538 | 1.68 | 1000 | 0.4388 | 48.2927 |
| 0.0864 | 2.1 | 1250 | 0.4283 | 44.9477 |
| 0.0885 | 2.52 | 1500 | 0.4429 | 44.8780 |
| 0.0765 | 2.94 | 1750 | 0.4405 | 46.2718 |
| 0.0614 | 3.36 | 2000 | 0.4431 | 45.1568 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1