Downloads · 30 days
1
7% of all-time downloads
whisper-medium-Encode-chinesemed
Hanhpt23/whisper-medium-Encode-chinesemed
whisper-medium-Encode-chinesemed is a automatic speech recognition model from Hanhpt23. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
15
Public
Parameters
764M
61.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 15, 2024
- Updated
- Jun 15, 2024
- SHA
- 05ea841e
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
openai/whisper-medium
This model is a fine-tuned version of openai/whisper-medium on the pphuc25/ChiMed dataset. It achieves the following results on the evaluation set:
- Loss: 1.5288
- Cer: 34.8039
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 | Cer |
|---|---|---|---|---|
| 0.8597 | 1.0 | 161 | 1.0181 | 51.8271 |
| 0.5092 | 2.0 | 322 | 1.1675 | 45.0980 |
| 0.3538 | 3.0 | 483 | 1.2404 | 43.5606 |
| 0.2113 | 4.0 | 644 | 1.3250 | 40.8868 |
| 0.1571 | 5.0 | 805 | 1.4131 | 42.8253 |
| 0.1351 | 6.0 | 966 | 1.4855 | 36.2077 |
| 0.1041 | 7.0 | 1127 | 1.5188 | 33.1996 |
| 0.0755 | 8.0 | 1288 | 1.4444 | 35.5615 |
| 0.0671 | 9.0 | 1449 | 1.4181 | 32.7540 |
| 0.0467 | 10.0 | 1610 | 1.4439 | 34.6702 |
| 0.0412 | 11.0 | 1771 | 1.5517 | 33.4447 |
| 0.031 | 12.0 | 1932 | 1.4488 | 31.8405 |
| 0.0234 | 13.0 | 2093 | 1.5155 | 31.9742 |
| 0.0185 | 14.0 | 2254 | 1.6007 | 32.4866 |
| 0.0125 | 15.0 | 2415 | 1.5451 | 37.9456 |
| 0.0062 | 16.0 | 2576 | 1.4836 | 31.5062 |
| 0.0009 | 17.0 | 2737 | 1.5238 | 30.1916 |
| 0.0002 | 18.0 | 2898 | 1.5149 | 30.7264 |
| 0.0001 | 19.0 | 3059 | 1.5268 | 34.6925 |
| 0.0002 | 20.0 | 3220 | 1.5288 | 34.8039 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- zh
- Created
- Jun 15, 2024
- Updated
- Jun 15, 2024