Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
speecht5_finetuned_russian-lang-dataset – AI Model by arevin42 | AlphaNeural AI
You can deploy this model and start earning money today!
arevin42
/
speecht5_finetuned_russian-lang-dataset
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
speecht5_finetuned_russian-lang-dataset
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: 0.4367
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: 500
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.5023
3.7710
1000
0.4574
0.4813
7.5454
2000
0.4457
0.4783
11.3197
3000
0.4397
0.4846
15.0940
4000
0.4367
Framework versions
Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.1
Tokenizers 0.21.0
