metadata
library_name: transformers
language:
- cz
license: cc-by-nc-sa-4.0
base_model: fav-kky/SpeechT5-base-cs-tts
tags:
- tts
- czech
- parlaspeechcz
- generated_from_trainer
datasets:
- ParlaspeechCZ
model-index:
- name: SpeechT5 TTS Czech
results: []
SpeechT5 TTS Czech
This model is a fine-tuned version of fav-kky/SpeechT5-base-cs-tts on the ParlaspeechCZ dataset.
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.50.3
- Pytorch 2.5.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.4