jenrish/whisper-small-ne

Whisper Small Ne - Jenny Poudel

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3732
• Cer: 10.4532

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: 16
• 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: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.5845	1.7857	100	0.5426	23.4003
0.306	3.5714	200	0.3589	15.5604
0.1432	5.3571	300	0.3052	12.7828
0.0634	7.1429	400	0.3039	12.4767
0.0331	8.9286	500	0.3155	11.6404
0.0134	10.7143	600	0.3395	10.8938
0.0047	12.5	700	0.3492	10.1023
0.0018	14.2857	800	0.3679	10.4682
0.0008	16.0714	900	0.3702	10.4980
0.0006	17.8571	1000	0.3732	10.4532

Framework versions

• Transformers 4.44.2
• Pytorch 1.13.1+cu117
• Datasets 2.21.0
• Tokenizers 0.19.1