You can deploy this model and start earning money today!

minhvn1433/
wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2

Name: wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2
Availability: InStock

transformers

safetensors

wav2vec2

automatic-speech-recognition

minhvn1433/vivos_wav2vec2

generated_from_trainer

custom_code

minhvn1433/wav2vec2-base-vi-vlsp2020

finetune

endpoints_compatible

Views

No views yet

wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2

This model is a fine-tuned version of minhvn1433/wav2vec2-base-vi-vlsp2020 on the MINHVN1433/VIVOS_WAV2VEC2 - NA dataset. It achieves the following results on the evaluation set:

Loss: 0.1892
Wer: 0.0755
Cer: 0.0320

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500.0
training_steps: 5500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1525	0.7622	500	0.1892	0.0755	0.0320
0.1116	1.5244	1000	0.1955	0.0792	0.0330
0.1040	2.2866	1500	0.1903	0.0798	0.0335
0.0977	3.0488	2000	0.1940	0.0799	0.0335
0.0963	3.8110	2500	0.2003	0.0801	0.0339
0.0919	4.5732	3000	0.2021	0.0804	0.0340
0.0913	5.3354	3500	0.2017	0.0792	0.0336
0.0921	6.0976	4000	0.2026	0.0794	0.0337
0.0918	6.8598	4500	0.1988	0.0795	0.0336
0.0874	7.6220	5000	0.2061	0.0791	0.0334
0.0848	8.3841	5500	0.1972	0.0794	0.0336

Framework versions

Transformers 5.12.1
Pytorch 2.11.0+cu128
Datasets 3.6.0
Tokenizers 0.22.2

minhvn1433/wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2

wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

minhvn1433/
wav2vec2-base-vi-vlsp2020-ft-vivos_wav2vec2