phucd/whisper-small-vi

Whisper - Vietnamese Model

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

• Loss: 0.6612
• Wer: 126.5455

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0204	5.59	1000	0.5415	136.8926
0.0005	11.17	2000	0.6213	120.9366
0.0003	16.76	3000	0.6507	125.1460
0.0002	22.35	4000	0.6612	126.5455

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 1.12.1
• Datasets 2.15.0
• Tokenizers 0.15.0