liqi03/whisper-large-v3-th-finetuned

Whisper Large V3 Th - Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0893
• Wer: 1436.2301

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
0.1636	0.3740	1000	0.1393	859.3431
0.1294	0.7479	2000	0.1121	989.6913
0.0608	1.1219	3000	0.0985	1657.8199
0.0617	1.4959	4000	0.0893	1436.2301

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1