whisper-tiny-khmer
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2487
- Wer: 1.3242
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: 6.25e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 80
- training_steps: 800
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4242 | 0.51 | 200 | 1.4528 | 1.1595 |
| 1.2641 | 1.01 | 400 | 1.3215 | 1.3512 |
| 1.1987 | 1.52 | 600 | 1.2649 | 1.2247 |
| 1.1687 | 2.03 | 800 | 1.2487 | 1.3242 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.6.dev0
- Tokenizers 0.14.1
- Downloads last month
- 2