Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
speecht5_tts_arabic_finetuned3 – AI Model by asaam | AlphaNeural AI
You can deploy this model and start earning money today!
asaam
/
speecht5_tts_arabic_finetuned3
like
0
transformers
safetensors
speecht5
text-to-audio
generated_from_trainer
microsoft/speecht5_tts
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
speecht5_tts_arabic_finetuned3
This model is a fine-tuned version of
microsoft/speecht5_tts
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.5148
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: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: 500
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.5979
6.2122
1000
0.5503
0.563
12.4243
2000
0.5327
0.5532
18.6365
3000
0.5234
0.5436
24.8487
4000
0.5148
Framework versions
Transformers 4.57.0
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1
