Downloads · 30 days
6
9% of all-time downloads
whisper-base-ko
youmi301/whisper-base-ko
whisper-base-ko is a automatic speech recognition model from youmi301. 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
66
Public
Parameters
72.6M
290 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Mar 12, 2025
- Updated
- Mar 16, 2025
- SHA
- ec556b72
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. -->
whisper-base-ko
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1055
- Wer Ortho: 7.6796
- Wer: 7.7097
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.1597 | 0.7184 | 500 | 0.2067 | 17.8437 | 17.9190 |
| 0.057 | 1.4368 | 1000 | 0.1392 | 17.8437 | 17.8889 |
| 0.0155 | 2.1552 | 1500 | 0.1144 | 8.7336 | 8.7939 |
| 0.0128 | 2.8736 | 2000 | 0.1055 | 7.6796 | 7.7097 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Mar 12, 2025
- Updated
- Mar 16, 2025