wav2vec2-tiengviet1 – AI Model by thang123 | AlphaNeural AI

You can deploy this model and start earning money today!

thang123/
wav2vec2-tiengviet1

like

0

automatic-speech-recognition

generated_from_trainer

endpoints_compatible

Views

No views yet

wav2vec2-tiengviet1

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.7302
Wer: 1.0118

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 300
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
14.8304	39.67	40	4.3168	1.0
5.5892	79.67	80	3.5454	1.0
5.2113	119.67	120	3.4845	1.0
4.9995	159.67	160	3.5783	1.0
4.7958	199.67	200	3.1850	1.0
4.4776	239.67	240	2.9864	1.0
4.2546	279.67	280	2.7302	1.0118

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2