Downloads · 30 days
14
33% of all-time downloads
whisper-small-GermanMed-v1
Hanhpt23/whisper-small-GermanMed-v1
whisper-small-GermanMed-v1 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
43
Public
Parameters
242M
28 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 7, 2024
- Updated
- Jun 8, 2024
- SHA
- aae1d34f
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-small
This model is a fine-tuned version of openai/whisper-small on the Hanhpt23/GermanMed dataset. It achieves the following results on the evaluation set:
- Loss: 5.4320
- Wer: 104.7646
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 |
|---|---|---|---|---|
| 3.0357 | 1.0 | 765 | 3.6479 | 111.4811 |
| 2.0376 | 2.0 | 1530 | 3.7281 | 105.4535 |
| 1.1924 | 3.0 | 2295 | 4.1208 | 101.4351 |
| 0.5922 | 4.0 | 3060 | 4.3857 | 100.8611 |
| 0.3146 | 5.0 | 3825 | 4.6652 | 101.6648 |
| 0.252 | 6.0 | 4590 | 4.7717 | 102.4684 |
| 0.1758 | 7.0 | 5355 | 4.9846 | 114.6383 |
| 0.1637 | 8.0 | 6120 | 5.0070 | 103.1573 |
| 0.1727 | 9.0 | 6885 | 5.0401 | 118.6567 |
| 0.1175 | 10.0 | 7650 | 5.1600 | 101.5499 |
| 0.1276 | 11.0 | 8415 | 5.1986 | 105.2239 |
| 0.1214 | 12.0 | 9180 | 5.2462 | 101.0907 |
| 0.1314 | 13.0 | 9945 | 5.2108 | 123.8232 |
| 0.0995 | 14.0 | 10710 | 5.3113 | 103.6165 |
| 0.1142 | 15.0 | 11475 | 5.3306 | 108.7256 |
| 0.1005 | 16.0 | 12240 | 5.3449 | 102.9277 |
| 0.0911 | 17.0 | 13005 | 5.4078 | 101.9518 |
| 0.0826 | 18.0 | 13770 | 5.3547 | 104.1332 |
| 0.0976 | 19.0 | 14535 | 5.3862 | 106.6590 |
| 0.0996 | 20.0 | 15300 | 5.4320 | 104.7646 |
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
- de
- Created
- Jun 7, 2024
- Updated
- Jun 8, 2024