vietnamese-regional-voice-classification-model
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vi on the LSVSC dataset. It achieves the following results on the evaluation set:
- Loss: 0.6087
- F1: 0.7853
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.0733 | 1.0 | 44 | 0.8828 | 0.7566 |
| 0.8621 | 2.0 | 88 | 0.7323 | 0.7653 |
| 0.7834 | 3.0 | 132 | 0.6746 | 0.7992 |
| 0.7098 | 4.0 | 176 | 0.8050 | 0.6410 |
| 0.6748 | 5.0 | 220 | 0.7053 | 0.7113 |
| 0.6335 | 6.0 | 264 | 0.6650 | 0.7491 |
| 0.6195 | 7.0 | 308 | 0.6096 | 0.7742 |
| 0.6118 | 8.0 | 352 | 0.6087 | 0.7853 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 142
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for thangtrungnguyen/vietnamese-regional-voice-classification-model
Base model
nguyenvulebinh/wav2vec2-base-vi