metadata
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: 4.7716
- Wer: 115.5556
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 |
|---|---|---|---|---|
| 2.2347 | 1.0 | 371 | 3.0537 | 111.1111 |
| 1.7551 | 2.0 | 742 | 3.0133 | 105.5556 |
| 1.3384 | 3.0 | 1113 | 3.2446 | 107.7778 |
| 0.7899 | 4.0 | 1484 | 3.5971 | 112.2222 |
| 0.424 | 5.0 | 1855 | 3.8711 | 117.7778 |
| 0.179 | 6.0 | 2226 | 4.0705 | 137.7778 |
| 0.0953 | 7.0 | 2597 | 4.2723 | 112.2222 |
| 0.0628 | 8.0 | 2968 | 4.4901 | 116.6667 |
| 0.0386 | 9.0 | 3339 | 4.3978 | 113.3333 |
| 0.0299 | 10.0 | 3710 | 4.5975 | 113.3333 |
| 0.0198 | 11.0 | 4081 | 4.6376 | 108.8889 |
| 0.0074 | 12.0 | 4452 | 4.6874 | 112.2222 |
| 0.0046 | 13.0 | 4823 | 4.6807 | 110.0000 |
| 0.0006 | 14.0 | 5194 | 4.7271 | 117.7778 |
| 0.0052 | 15.0 | 5565 | 4.7211 | 111.1111 |
| 0.0017 | 16.0 | 5936 | 4.7438 | 112.2222 |
| 0.0003 | 17.0 | 6307 | 4.7391 | 120.0 |
| 0.0002 | 18.0 | 6678 | 4.7585 | 120.0 |
| 0.0002 | 19.0 | 7049 | 4.7621 | 114.4444 |
| 0.0002 | 20.0 | 7420 | 4.7716 | 115.5556 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1