Downloads · 30 days
8
24% of all-time downloads
whisper-small-ko-E50_Yspeed
Gummybear05/whisper-small-ko-E50_Yspeed
whisper-small-ko-E50_Yspeed 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
34
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
- 1d499cb0
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
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: 0.1739
- Cer: 5.3865
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 |
|---|---|---|---|---|
| 0.3801 | 0.13 | 100 | 0.2603 | 6.2852 |
| 0.2383 | 0.26 | 200 | 0.2146 | 5.8329 |
| 0.2304 | 0.39 | 300 | 0.2099 | 5.6978 |
| 0.2025 | 0.52 | 400 | 0.1991 | 5.4922 |
| 0.172 | 0.64 | 500 | 0.1912 | 5.2279 |
| 0.1541 | 0.77 | 600 | 0.1841 | 5.8623 |
| 0.1538 | 0.9 | 700 | 0.1809 | 5.8917 |
| 0.0872 | 1.03 | 800 | 0.1781 | 5.6743 |
| 0.0693 | 1.16 | 900 | 0.1813 | 5.7213 |
| 0.0726 | 1.29 | 1000 | 0.1767 | 5.6156 |
| 0.0661 | 1.42 | 1100 | 0.1793 | 5.5451 |
| 0.0634 | 1.55 | 1200 | 0.1741 | 5.3630 |
| 0.0628 | 1.68 | 1300 | 0.1743 | 5.4570 |
| 0.0559 | 1.81 | 1400 | 0.1741 | 5.4335 |
| 0.0581 | 1.93 | 1500 | 0.1739 | 5.3865 |
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