Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisperfinetuning – AI Model by Yousafhasan | AlphaNeural AI
You can deploy this model and start earning money today!
Yousafhasan
/
whisperfinetuning
like
0
transformers
pytorch
tensorboard
whisper
automatic-speech-recognition
generated_from_trainer
openai/whisper-small
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisperfinetuning
This model is a fine-tuned version of
openai/whisper-small
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.9698
Wer: 14.4330
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: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
No log
1.0
1
0.9698
14.4330
No log
2.0
2
0.9698
14.4330
No log
3.0
3
0.9698
14.4330
No log
4.0
4
0.9698
14.4330
1.3785
5.0
5
0.9698
14.4330
Framework versions
Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0
