Tacotron 2 with Guided Attention trained on Synpaflex (Fr)

This repository provides a pretrained Tacotron2 trained with Guided Attention on Synpaflex dataset (Fr). For a detail of the model, we encourage you to read more about TensorFlowTTS.

Install TensorFlowTTS

First of all, please install TensorFlowTTS with the following command:

pip install TensorFlowTTS

Converting your Text to Mel Spectrogram

import numpy as np
import soundfile as sf
import yaml

import tensorflow as tf

from tensorflow_tts.inference import AutoProcessor
from tensorflow_tts.inference import TFAutoModel

processor = AutoProcessor.from_pretrained("tensorspeech/tts-tacotron2-synpaflex-fr")
tacotron2 = TFAutoModel.from_pretrained("tensorspeech/tts-tacotron2-synpaflex-fr")

text = "Oh, je voudrais tant que tu te souviennes Des jours heureux quand nous étions amis"

input_ids = processor.text_to_sequence(text)

decoder_output, mel_outputs, stop_token_prediction, alignment_history = tacotron2.inference(
    input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
    input_lengths=tf.convert_to_tensor([len(input_ids)], tf.int32),
    speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),

Referencing Tacotron 2

  author    = {Jonathan Shen and
               Ruoming Pang and
               Ron J. Weiss and
               Mike Schuster and
               Navdeep Jaitly and
               Zongheng Yang and
               Zhifeng Chen and
               Yu Zhang and
               Yuxuan Wang and
               R. J. Skerry{-}Ryan and
               Rif A. Saurous and
               Yannis Agiomyrgiannakis and
               Yonghui Wu},
  title     = {Natural {TTS} Synthesis by Conditioning WaveNet on Mel Spectrogram
  journal   = {CoRR},
  volume    = {abs/1712.05884},
  year      = {2017},
  url       = {http://arxiv.org/abs/1712.05884},
  archivePrefix = {arXiv},
  eprint    = {1712.05884},
  timestamp = {Thu, 28 Nov 2019 08:59:52 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1712-05884.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}

Referencing TensorFlowTTS

    author = {Minh Nguyen, Alejandro Miguel Velasquez, Erogol, Kuan Chen, Dawid Kobus, Takuya Ebata, 
    Trinh Le and Yunchao He},
    title = {TensorflowTTS},
    year = {2020},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\\url{https://github.com/TensorSpeech/TensorFlowTTS}},
Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.