whisper-large-v3-mn-ft

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: 0.5834

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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
• num_epochs: 6.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.4317	0.5903	500	0.7475
1.1836	1.1806	1000	0.5816
0.8169	1.7710	1500	0.5508
0.5782	2.3613	2000	0.5468
0.4928	2.9516	2500	0.5429
0.444	3.5419	3000	0.5626
0.2888	4.1322	3500	0.5678
0.283	4.7226	4000	0.5710
0.1823	5.3129	4500	0.5852
0.1725	5.9032	5000	0.5834

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.21.1