liqi03/whisper-large-v3-tr-ft

Whisper Large V3 tr ft - Chee Li

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

• Loss: 0.1394
• Wer: 8.9608

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-06
• 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
0.0368	5.5866	1000	0.1079	7.7474
0.003	11.1732	2000	0.1302	8.6030
0.0016	16.7598	3000	0.1373	8.7974
0.0013	22.3464	4000	0.1394	8.9608

Framework versions

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