liqi03/whisper-large-v3-tr-finetuned

Whisper Large V3 tr finetuned 3 - 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: 0.1369
• Wer: 33.0386

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
0.0095	5.5866	1000	0.1176	11.7358
0.0003	11.1732	2000	0.1281	33.0462
0.0001	16.7598	3000	0.1347	25.0208
0.0001	22.3464	4000	0.1369	33.0386

Framework versions

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