Downloads · 30 days
2
11% of all-time downloads
whisper-tiny-Encode-chinesemed
Hanhpt23/whisper-tiny-Encode-chinesemed
whisper-tiny-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
18
Public
Parameters
37.8M
3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
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
- 9f340f6a
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-tiny
This model is a fine-tuned version of openai/whisper-tiny on the pphuc25/ChiMed dataset. It achieves the following results on the evaluation set:
- Loss: 1.5036
- Cer: 34.0018
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 |
|---|---|---|---|---|
| 0.9949 | 1.0 | 161 | 1.1720 | 86.6756 |
| 0.6345 | 2.0 | 322 | 1.2101 | 74.7772 |
| 0.4273 | 3.0 | 483 | 1.2770 | 42.6025 |
| 0.2435 | 4.0 | 644 | 1.3652 | 44.5856 |
| 0.1437 | 5.0 | 805 | 1.4654 | 50.7353 |
| 0.097 | 6.0 | 966 | 1.4137 | 53.5873 |
| 0.0808 | 7.0 | 1127 | 1.4085 | 42.1569 |
| 0.049 | 8.0 | 1288 | 1.4790 | 38.6586 |
| 0.0392 | 9.0 | 1449 | 1.5276 | 40.6640 |
| 0.0283 | 10.0 | 1610 | 1.4854 | 42.5802 |
| 0.0164 | 11.0 | 1771 | 1.5004 | 39.7727 |
| 0.0126 | 12.0 | 1932 | 1.5267 | 41.9118 |
| 0.0124 | 13.0 | 2093 | 1.5349 | 36.7870 |
| 0.0061 | 14.0 | 2254 | 1.5172 | 35.6061 |
| 0.0018 | 15.0 | 2415 | 1.5075 | 34.0909 |
| 0.0032 | 16.0 | 2576 | 1.5066 | 34.5365 |
| 0.001 | 17.0 | 2737 | 1.4948 | 33.6453 |
| 0.0007 | 18.0 | 2898 | 1.5060 | 34.3137 |
| 0.0005 | 19.0 | 3059 | 1.5030 | 34.2246 |
| 0.0005 | 20.0 | 3220 | 1.5036 | 34.0018 |
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