kpriyanshu256/whisper-large-v2-as-600-32-1e-05-bn-Assamese
This model is a fine-tuned version of kpriyanshu256/whisper-large-v2-as-600-32-1e-05-bn on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2637
- Wer: 21.6928
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1915 | 1.1 | 50 | 0.2129 | 26.3851 |
| 0.0639 | 3.06 | 100 | 0.2305 | 23.0825 |
| 0.0192 | 5.03 | 150 | 0.2391 | 22.0538 |
| 0.0041 | 6.13 | 200 | 0.2637 | 21.6928 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2