Hugging Face's logo

vsisik
/
speecht5_tts_SK_v2

Text-to-Audio
Transformers
TensorBoard
Safetensors
Slovak
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_SK_v2 / README.md
vsisik's picture
vsisik
End of training
b5a813a verified
preview code
|
raw history blame contribute delete
No virus
1.86 kB
metadata
language:
  - sk
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS Slovak v2
    results: []

SpeechT5 TTS Slovak v2

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: 0.4301

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: 32
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • 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
0.5379 4.0 500 0.4771
0.4972 8.0 1000 0.4526
0.4854 12.0 1500 0.4409
0.4746 16.0 2000 0.4375
0.4733 20.0 2500 0.4335
0.4673 24.0 3000 0.4313
0.4577 28.0 3500 0.4306
0.4662 32.0 4000 0.4301

Framework versions

  • Transformers 4.40.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2