CheeLi03/whisper-polish

Whisper Turbo - Chee Li

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

• Loss: 0.2122
• Wer: 16.5502

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
0.0128	5.0251	1000	0.2026	11.1336
0.0021	10.0503	2000	0.2049	14.8868
0.0003	15.0754	3000	0.2108	13.6427
0.0001	20.1005	4000	0.2122	16.5502

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1