whisper-tiny-minds14 – AI Model by gouri100 | AlphaNeural AI

You can deploy this model and start earning money today!

gouri100/
whisper-tiny-minds14

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-tiny

endpoints_compatible

Views

No views yet

whisper-tiny-minds14

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

Loss: 0.5933
Wer Ortho: 0.3307
Wer: 0.3264

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: 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: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.2912	3.4483	100	0.4640	0.3621	0.3554
0.0476	6.8966	200	0.5141	0.3300	0.3194
0.0078	10.3448	300	0.5648	0.3350	0.3276
0.0026	13.7931	400	0.5879	0.3350	0.3312
0.0021	17.2414	500	0.5933	0.3307	0.3264

Framework versions

Transformers 4.53.2
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.2