whisper-small-kannada-transcribe – AI Model by shadabsayd | AlphaNeural AI

You can deploy this model and start earning money today!

shadabsayd/
whisper-small-kannada-transcribe

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-small

endpoints_compatible

Views

No views yet

whisper-small-kannada-transcribe

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

Loss: 0.3186
Wer: 46.5829

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: 64
eval_batch_size: 16
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: 500
training_steps: 5240
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1472	2.8517	750	0.1579	50.4750
0.0637	5.7034	1500	0.1520	46.9813
0.0185	8.5551	2250	0.2074	48.2991
0.0043	11.4068	3000	0.2651	46.5216
0.0013	14.2586	3750	0.2989	47.0120
0.0005	17.1103	4500	0.3186	46.5829

Framework versions

Transformers 4.48.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0