Downloads · 30 days
15
6% of all-time downloads
Vietnamese_Wav2Vec_Finetune_round3
pdabo1607/Vietnamese_Wav2Vec_Finetune_round3
Vietnamese_Wav2Vec_Finetune_round3 is a automatic speech recognition model from pdabo1607. 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
235
Public
Parameters
316M
20.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Nov 26, 2025
- Updated
- Nov 27, 2025
- SHA
- 35000568
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. -->
Vietnamese_Wav2Vec_Finetune_round3
This model is a fine-tuned version of pdabo1607/Vietnamese_Wav2Vec_Finetune_round2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5584
- Wer: 0.3267
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 500
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7995 | 0.9434 | 400 | 0.6439 | 0.3878 |
| 0.7842 | 1.8868 | 800 | 0.6291 | 0.3822 |
| 0.7837 | 2.8302 | 1200 | 0.6274 | 0.3709 |
| 0.7521 | 3.7736 | 1600 | 0.6054 | 0.3651 |
| 0.7347 | 4.7170 | 2000 | 0.5874 | 0.3617 |
| 0.7016 | 5.6604 | 2400 | 0.5702 | 0.3542 |
| 0.7089 | 6.6038 | 2800 | 0.5749 | 0.3491 |
| 0.6764 | 7.5472 | 3200 | 0.5636 | 0.3443 |
| 0.6805 | 8.4906 | 3600 | 0.5645 | 0.3392 |
| 0.6748 | 9.4340 | 4000 | 0.5781 | 0.3363 |
| 0.6755 | 10.3774 | 4400 | 0.5584 | 0.3366 |
| 0.6588 | 11.3208 | 4800 | 0.5599 | 0.3315 |
| 0.6725 | 12.2642 | 5200 | 0.5585 | 0.3280 |
| 0.6542 | 13.2075 | 5600 | 0.5621 | 0.3264 |
| 0.6718 | 14.1509 | 6000 | 0.5584 | 0.3267 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 4.4.1
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Nov 26, 2025
- Updated
- Nov 27, 2025