CheeLi03/whisper-tiny-vi-puct-5k

Whisper Tiny Viet 5k - Chee Li

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

• Loss: 1.0000
• Wer: 85.8097

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.258	4.7619	1000	0.7966	83.2124
0.0575	9.5238	2000	0.8570	138.7851
0.0117	14.2857	3000	0.9365	118.4239
0.0062	19.0476	4000	0.9840	90.4832
0.0046	23.8095	5000	1.0000	85.8097

Framework versions

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