Downloads · 30 days
16
3% of all-time downloads
wav2vec2-korean-finetuned2
daeunn/wav2vec2-korean-finetuned2
wav2vec2-korean-finetuned2 is a machine learning model from daeunn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
554
Public
Repo size
2.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jun 7, 2025
- Updated
- Jun 7, 2025
- SHA
- 44a0d504
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. -->
wav2vec2-korean-finetuned2
This model is a fine-tuned version of kresnik/wav2vec2-large-xlsr-korean on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2628
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9378 | 0.18 | 500 | 0.6153 |
| 0.7016 | 0.36 | 1000 | 0.4537 |
| 0.7075 | 0.55 | 1500 | 0.4040 |
| 0.5982 | 0.73 | 2000 | 0.3704 |
| 0.5354 | 0.91 | 2500 | 0.3453 |
| 0.4852 | 1.09 | 3000 | 0.3338 |
| 0.4603 | 1.27 | 3500 | 0.3181 |
| 0.4497 | 1.46 | 4000 | 0.3042 |
| 0.4489 | 1.64 | 4500 | 0.2928 |
| 0.441 | 1.82 | 5000 | 0.2839 |
| 0.4193 | 2.0 | 5500 | 0.2780 |
| 0.3736 | 2.18 | 6000 | 0.2785 |
| 0.3607 | 2.37 | 6500 | 0.2729 |
| 0.3529 | 2.55 | 7000 | 0.2685 |
| 0.365 | 2.73 | 7500 | 0.2644 |
| 0.3703 | 2.91 | 8000 | 0.2628 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.13.3
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jun 7, 2025
- Updated
- Jun 7, 2025