wav2vec2-base-vietnamese-control-dataset-75-epochs – AI Model by tuanmanh28 | AlphaNeural AI

You can deploy this model and start earning money today!

tuanmanh28/
wav2vec2-base-vietnamese-control-dataset-75-epochs

like

0

automatic-speech-recognition

generated_from_trainer

nguyenvulebinh/wav2vec2-base-vi

endpoints_compatible

Views

No views yet

wav2vec2_base_vietnamese_control_dataset_75_epochs

This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vi on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0584
Wer: 0.1728

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: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 75

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
16.8485	3.85	500	15.0708	1.0
7.7941	7.69	1000	5.1283	1.0
3.4391	11.54	1500	3.2167	1.0
3.116	15.38	2000	3.1172	1.0
3.0946	19.23	2500	3.1165	1.0
3.0478	23.08	3000	2.9426	1.0
2.4567	26.92	3500	1.6121	0.9993
1.2305	30.77	4000	0.5487	0.3630
0.5512	34.62	4500	0.2505	0.2364
0.3234	38.46	5000	0.1572	0.1869
0.2232	42.31	5500	0.1170	0.1782
0.1779	46.15	6000	0.0939	0.1772
0.145	50.0	6500	0.0830	0.1763
0.1383	53.85	7000	0.0739	0.1756
0.1161	57.69	7500	0.0681	0.1736
0.1054	61.54	8000	0.0630	0.1729
0.0958	65.38	8500	0.0620	0.1729
0.1028	69.23	9000	0.0582	0.1726
0.1015	73.08	9500	0.0584	0.1728

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3