Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
speecht5_finetuned_voxpopuli_es – AI Model by UnaiGurbindo | AlphaNeural AI
You can deploy this model and start earning money today!
UnaiGurbindo
/
speecht5_finetuned_voxpopuli_es
like
0
transformers
safetensors
speecht5
text-to-audio
generated_from_trainer
lt
facebook/voxpopuli
microsoft/speecht5_tts
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
speec T5 LT - Unai Gurbindo
This model is a fine-tuned version of
microsoft/speecht5_tts
on the Vox Populi LT dataset. It achieves the following results on the evaluation set:
Loss: 0.4978
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: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
0.6231
12.7
100
0.5834
0.5691
25.4
200
0.5259
0.5381
38.1
300
0.5030
0.5306
50.79
400
0.5016
0.521
63.49
500
0.4978
Framework versions
Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1
