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: 0.5085
• Wer: 142.4588
• Cer: 144.1035

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
0.094	3.07	1000	0.4069	121.3252	108.6949
0.0097	6.13	2000	0.4672	156.8577	132.2258
0.0022	9.2	3000	0.4975	142.9792	144.1017
0.0015	12.27	4000	0.5085	142.4588	144.1035

Framework versions

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