Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-small-ar – AI Model by lsuarezgo96 | AlphaNeural AI
You can deploy this model and start earning money today!
lsuarezgo96
/
whisper-small-ar
like
0
peft
tensorboard
safetensors
generated_from_trainer
ar
khaledalganem/sada2022
openai/whisper-small
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Small Ar-luis.s
This model is a fine-tuned version of
openai/whisper-small
on the SADA 2022 dataset. It achieves the following results on the evaluation set:
Loss: 3.2355
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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
3.2693
1.0
125
3.3144
3.1065
2.0
250
3.2476
2.9079
3.0
375
3.2355
Framework versions
PEFT 0.12.1.dev0
Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1
