metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-zh
results: []
whisper-base-zh
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4316
- Wer: 85.1032
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5085 | 0.2070 | 100 | 0.4641 | 89.6326 |
| 0.4047 | 0.4141 | 200 | 0.4315 | 88.2235 |
| 0.4156 | 0.6211 | 300 | 0.4055 | 86.8646 |
| 0.3826 | 0.8282 | 400 | 0.3907 | 87.2169 |
| 0.3087 | 1.0352 | 500 | 0.3806 | 86.9149 |
| 0.2709 | 1.2422 | 600 | 0.3775 | 87.0659 |
| 0.2707 | 1.4493 | 700 | 0.3681 | 85.7071 |
| 0.273 | 1.6563 | 800 | 0.3633 | 85.5561 |
| 0.2638 | 1.8634 | 900 | 0.3592 | 85.4051 |
| 0.1698 | 2.0704 | 1000 | 0.3613 | 85.6568 |
| 0.1849 | 2.2774 | 1100 | 0.3628 | 85.7574 |
| 0.1819 | 2.4845 | 1200 | 0.3645 | 85.4555 |
| 0.1712 | 2.6915 | 1300 | 0.3611 | 84.8515 |
| 0.1768 | 2.8986 | 1400 | 0.3573 | 84.3986 |
| 0.1265 | 3.1056 | 1500 | 0.3640 | 85.2038 |
| 0.1275 | 3.3126 | 1600 | 0.3661 | 85.4051 |
| 0.1277 | 3.5197 | 1700 | 0.3698 | 84.3986 |
| 0.1195 | 3.7267 | 1800 | 0.3684 | 85.3045 |
| 0.1176 | 3.9337 | 1900 | 0.3668 | 84.9522 |
| 0.0843 | 4.1408 | 2000 | 0.3764 | 84.9522 |
| 0.077 | 4.3478 | 2100 | 0.3801 | 84.8012 |
| 0.0853 | 4.5549 | 2200 | 0.3804 | 85.4051 |
| 0.0826 | 4.7619 | 2300 | 0.3827 | 84.8515 |
| 0.0759 | 4.9689 | 2400 | 0.3803 | 84.9522 |
| 0.0519 | 5.1760 | 2500 | 0.3959 | 84.9522 |
| 0.0578 | 5.3830 | 2600 | 0.3946 | 85.0528 |
| 0.0594 | 5.5901 | 2700 | 0.3956 | 85.0528 |
| 0.0598 | 5.7971 | 2800 | 0.3971 | 85.1535 |
| 0.0519 | 6.0041 | 2900 | 0.3980 | 84.7509 |
| 0.0421 | 6.2112 | 3000 | 0.4103 | 85.5058 |
| 0.0379 | 6.4182 | 3100 | 0.4124 | 84.9019 |
| 0.0363 | 6.6253 | 3200 | 0.4131 | 84.9019 |
| 0.0377 | 6.8323 | 3300 | 0.4149 | 85.2038 |
| 0.0286 | 7.0393 | 3400 | 0.4205 | 84.8515 |
| 0.0263 | 7.2464 | 3500 | 0.4257 | 84.6502 |
| 0.0309 | 7.4534 | 3600 | 0.4276 | 85.3548 |
| 0.0295 | 7.6605 | 3700 | 0.4282 | 85.3045 |
| 0.0266 | 7.8675 | 3800 | 0.4291 | 85.2038 |
| 0.0241 | 8.0745 | 3900 | 0.4308 | 85.1535 |
| 0.025 | 8.2816 | 4000 | 0.4316 | 85.1032 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1