CheeLi03/whisper-base-vi-puct-4k

Whisper Base Vietnamese Punctuation 4k - Chee Li

This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.8081
• Wer: 31.0898

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
0.1162	4.7619	1000	0.6436	31.9466
0.0088	9.5238	2000	0.7434	30.3875
0.0032	14.2857	3000	0.7912	31.6996
0.0025	19.0476	4000	0.8081	31.0898

Framework versions

• Transformers 4.43.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1