Hugging Face's logo

sumet
/
speecht5_finetuned_voxpopuli_es

Text-to-Speech
Transformers
PyTorch
Spanish
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Community
2
speecht5_finetuned_voxpopuli_es / README.md
sumet's picture
sumet
Update README.md
729359b
preview code
|
raw
history blame
1.42 kB
metadata
language:
  - es
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: speec T5 ES - Sumet
    results: []
pipeline_tag: text-to-speech

speec T5 ES - Sumet

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

  • eval_loss: 0.4434
  • eval_runtime: 126.5506
  • eval_samples_per_second: 19.802
  • eval_steps_per_second: 4.955
  • epoch: 3.41
  • step: 2400

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: 4
  • 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

Framework versions

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