Downloads · 30 days
13
13% of all-time downloads
Vietnamese_Wav2Vec_Finetune
pdabo1607/Vietnamese_Wav2Vec_Finetune
Vietnamese_Wav2Vec_Finetune 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
97
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 21, 2025
- Updated
- Nov 21, 2025
- SHA
- 651bf66c
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
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7778
- Wer: 0.5015
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: 1000
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.7238 | 0.9434 | 400 | 4.3969 | 1.0000 |
| 3.7833 | 1.8868 | 800 | 3.4483 | 1.0000 |
| 3.407 | 2.8302 | 1200 | 3.3647 | 1.0000 |
| 3.2531 | 3.7736 | 1600 | 2.6273 | 1.0000 |
| 2.3162 | 4.7170 | 2000 | 1.6377 | 0.9461 |
| 1.7377 | 5.6604 | 2400 | 1.2870 | 0.7850 |
| 1.4824 | 6.6038 | 2800 | 1.0638 | 0.6756 |
| 1.3022 | 7.5472 | 3200 | 0.9677 | 0.6144 |
| 1.2161 | 8.4906 | 3600 | 0.9012 | 0.5805 |
| 1.1507 | 9.4340 | 4000 | 0.8627 | 0.5556 |
| 1.1122 | 10.3774 | 4400 | 0.8179 | 0.5373 |
| 1.0667 | 11.3208 | 4800 | 0.8080 | 0.5243 |
| 1.0605 | 12.2642 | 5200 | 0.7947 | 0.5131 |
| 1.0229 | 13.2075 | 5600 | 0.7955 | 0.5057 |
| 1.0302 | 14.1509 | 6000 | 0.7778 | 0.5015 |
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 21, 2025
- Updated
- Nov 21, 2025