README.md

metadata

language:
  - es
license: mit
tags:
  - mabama-tts-es
  - generated_from_trainer
datasets:
  - ovieyra21/mabama-v4
model-index:
  - name: mabama-tts-v1
    results: []
pipeline_tag: text-to-speech

mabama-tts-v1

This model is a fine-tuned version of microsoft/speecht5_tts on the mabama-v4 dataset.

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.28.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3 Download them in the Files & versions tab.