Downloads · 30 days
5
13% of all-time downloads
whisper-small-ko-E50_Yspeed-SA
Gummybear05/whisper-small-ko-E50_Yspeed-SA
whisper-small-ko-E50_Yspeed-SA is a automatic speech recognition model from Gummybear05. 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
40
Public
Parameters
242M
14.5 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
- Dec 22, 2023
- Updated
- Dec 22, 2023
- SHA
- 706e742d
Base models
Datasets
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. -->
whisper-small-ko-E50_Yspeed-SA
This model is a fine-tuned version of openai/whisper-small on the aihub adult speed changed dataset. It achieves the following results on the evaluation set:
- Loss: 0.1719
- Cer: 6.2970
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.474 | 0.13 | 100 | 0.2830 | 6.2970 |
| 0.3153 | 0.26 | 200 | 0.2172 | 5.9857 |
| 0.2795 | 0.39 | 300 | 0.2128 | 6.1149 |
| 0.2458 | 0.52 | 400 | 0.1996 | 6.3205 |
| 0.2195 | 0.64 | 500 | 0.1924 | 5.2867 |
| 0.207 | 0.77 | 600 | 0.1839 | 4.9753 |
| 0.1976 | 0.9 | 700 | 0.1820 | 5.8506 |
| 0.1379 | 1.03 | 800 | 0.1764 | 4.9048 |
| 0.1191 | 1.16 | 900 | 0.1790 | 4.9401 |
| 0.128 | 1.29 | 1000 | 0.1750 | 4.8109 |
| 0.1122 | 1.42 | 1100 | 0.1764 | 4.8050 |
| 0.1134 | 1.55 | 1200 | 0.1724 | 4.9577 |
| 0.1192 | 1.68 | 1300 | 0.1718 | 6.3499 |
| 0.106 | 1.81 | 1400 | 0.1725 | 6.2852 |
| 0.0986 | 1.93 | 1500 | 0.1719 | 6.2970 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Dec 22, 2023
- Updated
- Dec 22, 2023