Whisper Tiny Mongolian - Cheryl
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: 0.9725
- Wer: 50.9334
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: 64
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0053 | 16.01 | 1000 | 0.7965 | 52.4945 |
| 0.0004 | 33.01 | 2000 | 0.8716 | 49.8253 |
| 0.0002 | 50.01 | 3000 | 0.9256 | 50.1037 |
| 0.0001 | 67.01 | 4000 | 0.9542 | 50.3275 |
| 0.0001 | 84.01 | 5000 | 0.9725 | 50.9334 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
