vietnamese-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: 0.0971
• F1: 0.9831

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.501	0.9931	36	0.2733	0.9699
0.1647	1.9862	72	0.1368	0.9787
0.1045	2.9793	108	0.1080	0.9820
0.0903	4.0	145	0.0972	0.9836
0.1065	4.9655	180	0.0971	0.9831

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0