Downloads · 30 days
4
11% of all-time downloads
whisper-small-ko-Y2
Gummybear05/whisper-small-ko-Y2
whisper-small-ko-Y2 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
36
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 21, 2023
- Updated
- Dec 21, 2023
- SHA
- f048789d
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-Y-SA2
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: 0.2617
- Cer: 6.4967
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 |
|---|---|---|---|---|
| 0.245 | 0.13 | 100 | 0.2925 | 8.0240 |
| 0.1373 | 0.26 | 200 | 0.2754 | 7.3719 |
| 0.1094 | 0.39 | 300 | 0.2801 | 7.4189 |
| 0.1216 | 0.52 | 400 | 0.2645 | 7.3191 |
| 0.0964 | 0.64 | 500 | 0.2672 | 7.1722 |
| 0.0919 | 0.77 | 600 | 0.2690 | 7.0900 |
| 0.0925 | 0.9 | 700 | 0.2673 | 7.0547 |
| 0.038 | 1.03 | 800 | 0.2590 | 6.8374 |
| 0.0291 | 1.16 | 900 | 0.2617 | 6.6906 |
| 0.0378 | 1.29 | 1000 | 0.2622 | 6.7669 |
| 0.0326 | 1.42 | 1100 | 0.2675 | 6.7082 |
| 0.037 | 1.55 | 1200 | 0.2619 | 6.6142 |
| 0.0315 | 1.68 | 1300 | 0.2607 | 6.5261 |
| 0.0313 | 1.81 | 1400 | 0.2600 | 6.4791 |
| 0.0321 | 1.93 | 1500 | 0.2617 | 6.4967 |
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 21, 2023
- Updated
- Dec 21, 2023