Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
speecht5_finetuned_covost2_en_es – AI Model by sophiayk20 | AlphaNeural AI
You can deploy this model and start earning money today!
sophiayk20
/
speecht5_finetuned_covost2_en_es
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_finetuned_covost2_en_es
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: 0.4824
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
training_steps: 4000
Training results
Training Loss
Epoch
Step
Validation Loss
0.534
7.1422
1000
0.4944
0.5118
14.2844
2000
0.4865
0.4981
21.4267
3000
0.4811
0.4922
28.5689
4000
0.4824
Framework versions
Transformers 4.48.2
Pytorch 2.5.1+cu124
Tokenizers 0.21.0
