uaspeech-large-finetune-long-evals-30-11-11AM

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: 0.3481

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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
0.2252	0.2070	500	0.3504
0.1217	0.4139	1000	0.3028
0.071	0.6209	1500	0.3409
0.0581	0.8278	2000	0.3390
0.0279	1.0348	2500	0.3261
0.0132	1.2417	3000	0.3258
0.006	1.4487	3500	0.3280
0.0077	1.6556	4000	0.3553
0.0094	1.8626	4500	0.3516
0.0043	2.0695	5000	0.3481

Framework versions

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