Hugging Face's logo

Nyanmero
/
speecht5-tts-vie

Text-to-Audio
Transformers
TensorBoard
Safetensors
Vietnamese
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5-tts-vie / README.md
Nyanmero's picture
Nyanmero
End of training
2364992 verified
preview code
|
raw
history blame contribute delete
1.47 kB
metadata
language:
  - vie
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: Fine-tuned SpeechT5 on Vietnamese TTS
    results: []

Fine-tuned SpeechT5 on Vietnamese TTS

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

  • eval_loss: 0.5410
  • eval_runtime: 292.5007
  • eval_samples_per_second: 42.496
  • eval_steps_per_second: 2.656
  • epoch: 8.2736
  • step: 15000

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 12000
  • training_steps: 100000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1