no-voice-clone-large-finetune-test

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

• Loss: 0.4622
• Wer: 20.1897

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0088	4.6729	250	0.5014	21.1681
0.0079	9.3458	500	0.5158	29.2321
0.0001	14.0187	750	0.4311	23.9253
0.0	18.6916	1000	0.4457	20.5752
0.0	23.3645	1250	0.4520	20.6048
0.0	28.0374	1500	0.4560	20.1897
0.0	32.7103	1750	0.4588	20.1601
0.0	37.3832	2000	0.4607	20.1304
0.0	42.0561	2250	0.4618	20.2490
0.0	46.7290	2500	0.4622	20.1897

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3