Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-noise – AI Model by Dearlie | AlphaNeural AI
You can deploy this model and start earning money today!
Dearlie
/
whisper-noise
like
0
transformers
tensorboard
safetensors
whisper
automatic-speech-recognition
generated_from_trainer
ko
AIHub/noise
openai/whisper-base
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Base Noise Ko - Dearlie
This model is a fine-tuned version of
openai/whisper-base
on the Noise Data dataset. It achieves the following results on the evaluation set:
Loss: 2.7443
Cer: 75.4471
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: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Cer
2.9811
0.8780
1000
2.9947
76.6578
2.8567
1.7559
2000
2.8397
75.8959
2.7019
2.6339
3000
2.7677
75.6193
2.7047
3.5119
4000
2.7443
75.4471
Framework versions
Transformers 4.41.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1
