Whisper Tiny Marathi
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4618
- Wer: 41.6451
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: 16
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6182 | 0.95 | 200 | 0.6224 | 53.6706 |
| 0.4364 | 1.9 | 400 | 0.5200 | 47.2071 |
| 0.3668 | 2.84 | 600 | 0.4830 | 44.4890 |
| 0.294 | 3.79 | 800 | 0.4671 | 42.8562 |
| 0.2729 | 4.74 | 1000 | 0.4642 | 42.1214 |
| 0.2401 | 5.69 | 1200 | 0.4614 | 41.6996 |
| 0.2212 | 6.64 | 1400 | 0.4618 | 41.7778 |
| 0.2093 | 7.58 | 1600 | 0.4618 | 41.6451 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2