whisper-tiny – AI Model by OmBenz | AlphaNeural AI

You can deploy this model and start earning money today!

OmBenz/
whisper-tiny

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-tiny

endpoints_compatible

Views

No views yet

whisper-tiny

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

Loss: 0.5278
Wer Ortho: 0.3436
Wer: 0.3383

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 120

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
3.4388	1.43	20	2.2576	0.5022	0.4038
1.1317	2.86	40	0.5981	0.4047	0.3932
0.3235	4.29	60	0.4967	0.3720	0.3707
0.138	5.71	80	0.5035	0.3356	0.3282
0.0563	7.14	100	0.5198	0.3362	0.3294
0.033	8.57	120	0.5278	0.3436	0.3383

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0