Hugging Face's logo

hugse
/
speecht5_tts_voxpopuli_hr

Text-to-Audio
Transformers
TensorBoard
Safetensors
Croatian
speecht5
hrvatski
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_voxpopuli_hr / README.md
hugse's picture
hugse
End of training
55e1b18 verified
preview code
|
raw
history blame
1.68 kB
metadata
language:
  - hr
license: mit
base_model: microsoft/speecht5_tts
tags:
  - hrvatski
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS Croatian
    results: []

SpeechT5 TTS Croatian

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: 0.4518

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: 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
0.4845 32.2581 1000 0.4559
0.4608 64.5161 2000 0.4489
0.4499 96.7742 3000 0.4497
0.4433 129.0323 4000 0.4518

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1