whisper-tiny-ArtCreativity-V3

This model is a fine-tuned version of wwwtwwwt/whisper-tiny-no-specific-topic-V3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7069
• Wer: 35.7323

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: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5196	1.0108	1000	0.7409	42.5077
0.486	2.0217	2000	0.6789	37.7554
0.2484	3.0325	3000	0.6781	35.7123
0.5309	4.0433	4000	0.7107	37.4893
0.2505	5.0542	5000	0.7074	36.2444
0.2178	6.065	6000	0.7069	35.7323

Framework versions

• Transformers 4.50.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.0