Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
whisper-small-darija-lora – AI Model by Hossamfazaz | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
Hossamfazaz
/
whisper-small-darija-lora
like
0
peft
tensorboard
safetensors
adapter
lora
transformers
openai/whisper-small
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
whisper-small-darija-lora
This model is a fine-tuned version of
openai/whisper-small
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 2.1139
Wer: 76.5517
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: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
2.9448
1.0
28
2.6142
81.8832
2.3772
2.0
56
2.2338
77.0403
2.0813
3.0
84
2.1139
76.5517
Framework versions
PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1
