whisper-vietnamese-cntt2

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

• Loss: 0.4533
• Wer: 15.7376
• Cer: 8.3598

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
0.1453	2.87	1000	0.3516	16.2580	8.7008
0.0199	5.73	2000	0.4018	15.9861	8.5303
0.0076	8.6	3000	0.4292	15.7531	8.4522
0.0045	11.46	4000	0.4533	15.7376	8.3598

Framework versions

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