Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
khaled_lakhdher_speecht5_finetuned – AI Model by KhaledLakhdher | AlphaNeural AI
You can deploy this model and start earning money today!
KhaledLakhdher
/
khaled_lakhdher_speecht5_finetuned
like
0
transformers
tensorboard
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
khaled_lakhdher_speecht5_finetuned
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: 0.4461
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: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.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: 100
training_steps: 500
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
5.7242
8.3137
100
0.5648
4.4771
16.6275
200
0.4661
4.2475
24.9412
300
0.4560
4.1729
33.3137
400
0.4486
4.0969
41.6275
500
0.4461
Framework versions
Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.3.2
Tokenizers 0.21.0
