Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
speecht5_tts_voxpopuli_pl_v4 – AI Model by kuba-cherryb | AlphaNeural AI
You can deploy this model and start earning money today!
kuba-cherryb
/
speecht5_tts_voxpopuli_pl_v4
like
0
transformers
tensorboard
safetensors
speecht5
text-to-audio
generated_from_trainer
pl
facebook/voxpopuli
microsoft/speecht5_tts
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
SpeechT5 TTS Polish v4
This model is a fine-tuned version of
microsoft/speecht5_tts
on the VoxPopuli dataset. It achieves the following results on the evaluation set:
Loss: 0.4412
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: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use 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
0.5036
5.0251
1000
0.4625
0.4852
10.0503
2000
0.4475
0.4754
15.0754
3000
0.4427
0.4781
20.1005
4000
0.4412
Framework versions
Transformers 4.49.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0
