metadata
language:
- zh
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: openai/whisper-tiny
results: []
openai/whisper-tiny
This model is a fine-tuned version of openai/whisper-tiny on the Hanhpt23/ChineseMed dataset. It achieves the following results on the evaluation set:
- Loss: 5.4554
- Wer: 132.7991
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: 0.0001
- 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: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0558 | 1.0 | 2222 | 3.0833 | 127.4184 |
| 2.5492 | 2.0 | 4444 | 3.0648 | 130.1088 |
| 2.0618 | 3.0 | 6666 | 3.2779 | 112.4785 |
| 1.5376 | 4.0 | 8888 | 3.6124 | 132.1122 |
| 1.1944 | 5.0 | 11110 | 3.9546 | 112.3641 |
| 0.8561 | 6.0 | 13332 | 4.3130 | 125.9874 |
| 0.6536 | 7.0 | 15554 | 4.5104 | 138.4659 |
| 0.4346 | 8.0 | 17776 | 4.7482 | 113.7378 |
| 0.411 | 9.0 | 19998 | 4.9091 | 134.0584 |
| 0.3214 | 10.0 | 22220 | 4.9981 | 124.9571 |
| 0.3408 | 11.0 | 24442 | 5.0642 | 137.0922 |
| 0.2991 | 12.0 | 26664 | 5.1118 | 116.9433 |
| 0.3083 | 13.0 | 28886 | 5.2996 | 132.7418 |
| 0.2714 | 14.0 | 31108 | 5.3376 | 115.1116 |
| 0.3389 | 15.0 | 33330 | 5.3140 | 125.2433 |
| 0.2698 | 16.0 | 35552 | 5.3652 | 116.7716 |
| 0.2698 | 17.0 | 37774 | 5.3976 | 118.8323 |
| 0.2836 | 18.0 | 39996 | 5.4280 | 123.9267 |
| 0.2192 | 19.0 | 42218 | 5.4235 | 131.3108 |
| 0.2257 | 20.0 | 44440 | 5.4554 | 132.7991 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1