dvshah13's picture
Upload 9 files
9808ccc
metadata
language:
  - es
license: mit
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 spanish Speaker
    results: []
pipeline_tag: text-to-speech

SpeechT5 spanish Speaker

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:

  • Loss: 0.4448

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

Training results

Training Loss Epoch Step Validation Loss
0.5134 4.32 1000 0.4636
0.4907 8.64 2000 0.4527
0.4814 12.97 3000 0.4459
0.4777 17.29 4000 0.4448

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3