whisper-small-csclean-yt

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

• Loss: 1.0503
• Cer: 41.9280

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: 5e-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• 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: 150
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
1.21	0.7576	400	1.1675	47.2543
0.8072	1.5152	800	1.0822	43.8429
0.5896	2.2727	1200	1.0503	41.9831
0.5382	3.0303	1600	1.0398	41.9941
0.4952	3.7879	2000	1.0503	41.9280

Framework versions

• Transformers 4.52.4
• Pytorch 2.1.0+cu118
• Datasets 3.6.0
• Tokenizers 0.21.2