ovieyra21's picture
first commit
ba2681d
metadata
language:
  - es
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - ylacombe/google-chilean-spanish
model-index:
  - name: SpeechT5 TTS mabama
    results: []

SpeechT5 TTS mabama

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

  • Loss: 0.3995

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: 1000
  • training_steps: 1200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4516 25.53 1200 0.3995

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2