whisper_base_to_pf10h – AI Model by rishabhjain16 | AlphaNeural AI

You can deploy this model and start earning money today!

rishabhjain16/
whisper_base_to_pf10h

like

0

automatic-speech-recognition

generated_from_trainer

endpoints_compatible

Views

No views yet

openai/whisper-base

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

Loss: 0.1929
Wer: 4.3549

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: 32
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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0326	10.0	500	0.1670	5.0398
0.0019	20.0	1000	0.1728	4.5113
0.0008	30.01	1500	0.1820	4.4071
0.0005	40.01	2000	0.1847	4.3773
0.0004	51.0	2500	0.1886	4.3549
0.0003	61.0	3000	0.1910	4.3475
0.0003	71.01	3500	0.1925	4.3549
0.0002	81.01	4000	0.1929	4.3549

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.9.1.dev0
Tokenizers 0.13.2