Hugging Face's logo

flavioegoncalves
/
speecht5_tts_portuguese

Text-to-Audio
Transformers
TensorBoard
Safetensors
Portuguese
speecht5
tts
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
speecht5_tts_portuguese / README.md
flavioegoncalves's picture
flavioegoncalves
End of training
63c547f verified
preview code
|
raw
history blame
1.68 kB
metadata
language:
  - pt
license: mit
base_model: microsoft/speecht5_tts
tags:
  - tts
  - generated_from_trainer
datasets:
  - multilingual_librispeech
model-index:
  - name: SpeechT5 TTS Portuguese
    results: []

SpeechT5 TTS Portuguese

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

  • Loss: 0.3677

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: 2
  • 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4263 3.88 1000 0.3850
0.4078 7.76 2000 0.3719
0.4017 11.63 3000 0.3694
0.403 15.51 4000 0.3677

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0