Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
songhoy-asr-v0-ic – AI Model by sudoping01 | AlphaNeural AI
You can deploy this model and start earning money today!
sudoping01
/
songhoy-asr-v0-ic
like
0
peft
safetensors
generated_from_trainer
openai/whisper-large-v2
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
songhoy-asr-v0-ic
This model is a fine-tuned version of
openai/whisper-large-v2
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.2345
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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 6
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.228
1.0
245
0.2366
0.1739
2.0
490
0.2013
0.1309
3.0
735
0.1966
0.1003
4.0
980
0.1985
0.0728
5.0
1225
0.2158
0.0565
5.9775
1464
0.2345
Framework versions
PEFT 0.14.1.dev0
Transformers 4.50.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0
