Sagicc/whisper-large-v3-turbo-sr-v2

Whisper Large v3 Turbo Sr Test

This model is in test phase DO NOT USE IT ... YET

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

• Loss: 0.1195
• Wer: 0.1378

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
0.6455	0.2439	500	0.1869	0.1928
0.5858	0.4878	1000	0.1694	0.1870
0.5608	0.7317	1500	0.1507	0.1641
0.4547	0.9756	2000	0.1388	0.1542
0.3905	1.2195	2500	0.1341	0.1461
0.3857	1.4634	3000	0.1291	0.1450
0.3656	1.7073	3500	0.1243	0.1415
0.3369	1.9512	4000	0.1195	0.1378

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.20.3