whisper-vietnamese-2

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: 0.4398
• Wer: 15.4165
• Cer: 8.2906

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1394	2.87	1000	0.3392	15.8696	8.6357
0.0182	5.73	2000	0.3863	15.6521	8.2710
0.008	8.6	3000	0.4126	15.2042	8.2426
0.0052	11.46	4000	0.4398	15.4165	8.2906

Framework versions

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