Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

📚 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

Robust Speech Recognition via Large-Scale Weak Supervision

A multi-voice TTS system trained with an emphasis on quality

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Fast and memory-efficient exact attention

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

An unofficial PyTorch implementation of the audio LM VALL-E

PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Clone a voice in 5 seconds to generate arbitrary speech in real-time

此项目是机器学习(Machine Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

TTS model based on Transformer.

Accompanying source code for Machine Learning with TensorFlow. Refer to the book for step-by-step explanations.

DeepMind's Tacotron-2 Tensorflow implementation

机器学习相关教程

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model

This is now the official location of the Merlin project.

Computation using data flow graphs for scalable machine learning