Hugging Face's logo

Dulence
/
speecht5_tts_voxpopuli_hr

Text-to-Audio
Transformers
PyTorch
Croatian
speecht5
dusan
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_tts_voxpopuli_hr / README.md
Dulence's picture
Dulence
End of training
c069b53
preview code
|
raw
history blame contribute delete
1.62 kB
metadata
language:
  - hr
license: mit
base_model: microsoft/speecht5_tts
tags:
  - dusan
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS Hrvatski
    results: []

SpeechT5 TTS Hrvatski

This model is a fine-tuned version of microsoft/speecht5_tts on the VoxPopuli hr dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4304

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: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss
0.4915 3.24 1000 0.4504
0.4757 6.49 2000 0.4366
0.4653 9.73 3000 0.4318
0.4636 12.98 4000 0.4304

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3