CKSINGH/whisper-small-hi

Whisper Small Hi - CKS 111102 gramin dataset over common voice

This model is a fine-tuned version of [fine tuned openai/whisper-small](https://huggingface.co./fine tuned openai/whisper-small) on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2500
• Wer: 27.5791

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: 1.75e-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: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2056	1.92	100	0.1679	27.0708
0.065	3.85	200	0.2057	28.1062
0.0153	5.77	300	0.2324	28.0873
0.0031	7.69	400	0.2461	27.5979
0.0013	9.62	500	0.2500	27.5791

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1