(Multi Speaker) Text-To-Speech (TTS) project

Speech synthesis with conditioning on very small dataset. Using Nvidia's Tacotron2 and WaveGlow models with Pytorch.

Real-Time High-Fidelity Speech Synthesis without GPU

Command-line interface and Python library for synthesizing English texts into speech.

Web app, command-line interface and Python library for synthesizing Chinese texts into speech.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Extension to add advanced features to Wunjo AI

[Last Updated 2021] TTS from Cookie. Messy and experimental!

PyTorch implementation of NVIDIA WaveGlow with constant memory cost.

Multi-Speaker Pytorch FastSpeech2: Fast and High-Quality End-to-End Text to Speech ✊

homework for deep generation. Combine FastSpeech2 with different vocoders ⭐REFERENCE (modify origin repos): https://github.com/ming024/FastSpeech2 https://github.com/NVIDIA/waveglow https://github.com/mindslab-ai/univnet https://github.com/jik876/hifi-gan

W.I.P. talking discord buddy! Uses any finetuned (or not) GPT-2 model along with a custom Tacotron2 + Waveglow model to create a custom discord bot that actively participates in voice chats.

This is a bot that will accept voice messages and reply back in voice messages.

Another PyTorch implementation of Tacotron2 MMI (with waveglow) which supports n_frames_per_step>1 mode(reduction windows) and diagonal guided attention for robust alignments.

Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow

Text-to-Speech models based on the NVIDIA's examples.

Waveglow Tacotron2 text to speech

WaveGLow -- A Flow-based Generative Network for Speech Synthesis . PyTorch Code modified to run on TPUs .

Text To Speech (TTS) GUI wrapper for NVIDIA Tacotron 2+Waveglow. For custom Twitch TTS.

Tensorflow 2.0 implementation of the Nvidia Waveglow model