Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-Franko-CS-v0-new – AI Model by Moamen-dcp | AlphaNeural AI
You can deploy this model and start earning money today!
Moamen-dcp
/
whisper-Franko-CS-v0-new
like
0
peft
tensorboard
safetensors
generated_from_trainer
openai/whisper-large-v3-turbo
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-Franko-CS-v0-new
This model is a fine-tuned version of
openai/whisper-large-v3-turbo
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.1471
Overall Composite Score: 0.0
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: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Overall Composite Score
0.9821
0.6380
400
1.1471
0.0
0.8181
1.2759
800
1.0906
0.0
0.7859
1.9139
1200
1.0744
0.0
0.7061
2.5518
1600
1.0760
0.0
Framework versions
PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.7.1+cu128
Datasets 3.6.0
Tokenizers 0.21.1
