Downloads · 30 days
5
9% of all-time downloads
whisper-small-ko-Yspeed
Gummybear05/whisper-small-ko-Yspeed
whisper-small-ko-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
54
Public
Repo size
15.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 6, 2023
- Updated
- Sep 6, 2023
- SHA
- e029ec1b
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-Yspeed
This model is a fine-tuned version of openai/whisper-small on the aihub elder over 70 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3415
- Cer: 8.3071
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: 2e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.362 | 0.3 | 100 | 0.3138 | 8.5089 |
| 0.283 | 0.59 | 200 | 0.3211 | 9.1438 |
| 0.2666 | 0.89 | 300 | 0.3264 | 9.4167 |
| 0.1077 | 1.19 | 400 | 0.3124 | 8.9124 |
| 0.1022 | 1.48 | 500 | 0.3241 | 9.0666 |
| 0.0893 | 1.78 | 600 | 0.3141 | 8.4555 |
| 0.0314 | 2.07 | 700 | 0.3244 | 8.3665 |
| 0.0305 | 2.37 | 800 | 0.3339 | 8.6394 |
| 0.0347 | 2.67 | 900 | 0.3289 | 8.8412 |
| 0.0277 | 2.96 | 1000 | 0.3386 | 10.1288 |
| 0.0106 | 3.26 | 1100 | 0.3433 | 8.7284 |
| 0.01 | 3.56 | 1200 | 0.3405 | 8.3902 |
| 0.0107 | 3.85 | 1300 | 0.3424 | 9.2031 |
| 0.0041 | 4.15 | 1400 | 0.3370 | 8.4139 |
| 0.0048 | 4.44 | 1500 | 0.3408 | 8.4080 |
| 0.0031 | 4.74 | 1600 | 0.3415 | 8.3071 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Sep 6, 2023
- Updated
- Sep 6, 2023