whisper-vietnamese

This model is a fine-tuned version of duytran3112/whisper-sm-vivos on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5065
• Wer: 143.8155
• Cer: 157.5871

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.0953	3.07	1000	0.4070	131.4363	111.3538
0.0089	6.13	2000	0.4713	159.9544	148.2014
0.003	9.2	3000	0.4932	139.2248	152.0525
0.0015	12.27	4000	0.5065	143.8155	157.5871

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3