There are 4 repositories under tacotron2 topic.
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
A Python/Pytorch app for easily synthesising human voices
一个使用C++编写的音频处理软件
Wunjo AI: Synthesize & clone voices in English, Russian & Chinese, real-time speech recognition, deepfake face & lips animation, face swap with one photo, change video by text prompts, segmentation, and retouching. Open-source, local & free.
PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Parallel WaveGAN)
Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.
Tensorflow implementation of Chinese/Mandarin TTS (Text-to-Speech) based on Tacotron-2 model.
GPT + Tacotron2/VITS + Live2D = CyberWaifu
TTS models for Arabic (Tacotron2, FastPitch)
a PyTorch implementation of Lip2Wav
PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
an improved version of Real-time-voice-cloning
Text To Speech (TTS) GUI wrapper for NVIDIA Tacotron 2+Waveglow. For custom Twitch TTS.
German Tacotron 2 and Multi-band MelGAN in TensorFlow with TF Lite inference support
PyTorch implementation of Tacotron-2. Tacotron-2 的 PyTorch 实现。
Tacotron 2 training notebook supporting Japanese, French, and Mandarin
This repository contain the code of the main part of my master thesis degree at Politecnico di Torino in Data science & Engineering
Training Tacotron2 for Persian language as a Persian text-to-speech
EC499: Major Project
Pytorch implementation of Tacotron 2 (https://arxiv.org/pdf/1712.05884.pdf)
Extension to add advanced features to Wunjo AI
Catalan Text to Speech
A dataset for Mario's voice (Charles Martinet), from the Super Mario franchise. More info here: https://uberduck.ai/about
Este proyecto explora la síntesis de voz para replicar el distintivo estilo vocal de Neng de Castefa. Analiza desafíos técnicos, tecnologías y presenta experimentos y resultados en la recreación de su voz única.
Converting text to audio and applying audio augmentation
Synthese vocale avec conditionnement sur tres petit jeu de données. Utilisation des modeles Tacotron2 et WaveGlow de Nvidia avec Pytorch.