nr-whisper-tiny – AI Model by dadajuan123 | AlphaNeural AI

You can deploy this model and start earning money today!

dadajuan123/
nr-whisper-tiny

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-tiny

endpoints_compatible

Views

No views yet

nr-whisper-tiny

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

Loss: 1.0791
Wer: 400.0

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1814	100.0	100	1.2428	200.0
0.0001	200.0	200	1.0974	200.0
0.0	300.0	300	1.0920	300.0
0.0	400.0	400	1.0876	400.0
0.0	500.0	500	1.0842	400.0
0.0	600.0	600	1.0816	400.0
0.0	700.0	700	1.0803	400.0
0.0	800.0	800	1.0799	400.0
0.0	900.0	900	1.0793	400.0
0.0	1000.0	1000	1.0791	400.0

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2
Datasets 2.16.1
Tokenizers 0.15.1