whisper-v3-LoRA-en_students_test_2

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

• Loss: 0.3590
• Wer: 12.3268

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 100000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9094	0.1270	500	0.6347	24.3686
0.5517	0.2541	1000	0.4835	18.0769
0.5364	0.3811	1500	0.4330	15.1149
0.5503	0.5081	2000	0.4113	13.6524
0.6521	0.6352	2500	0.3987	13.5897
0.6044	0.7622	3000	0.3912	13.0538
0.5487	0.8892	3500	0.3835	12.6119
0.5297	1.0163	4000	0.3791	12.4408
0.46	1.1433	4500	0.3751	12.3525
0.4947	1.2703	5000	0.3721	12.1415
0.524	1.3974	5500	0.3682	13.0139
0.4743	1.5244	6000	0.3649	13.3388
0.5338	1.6514	6500	0.3621	12.9397
0.5162	1.7785	7000	0.3597	13.3246
0.5004	1.9055	7500	0.3590	12.3268

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1