Whisper Small Hindi - Sanchit Gandhi
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: 0.3323
- Wer: 31.3299
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: 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 |
|---|---|---|---|---|
| 0.1464 | 1.22 | 1000 | 0.3049 | 36.8492 |
| 0.0636 | 2.44 | 2000 | 0.2910 | 32.8875 |
| 0.0191 | 3.67 | 3000 | 0.3117 | 31.7828 |
| 0.0096 | 4.89 | 4000 | 0.3323 | 31.3299 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.