1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

The official implementation of HierSpeech++

淘宝、天猫半价抢购，抢电视、抢茅台，干死黄牛党

大麦网演唱会抢票软件，一个基于 tauri + rust + vue 调用接口的抢票软件。

大麦网演唱会抢票脚本

大麦网抢票脚本

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

PyTorch implementation of Densely Connected Time Delay Neural Network

优化版本的京东茅台抢购神器

A game theoretic approach to explain the output of any machine learning model.

An Open Source Tools for Speaker Recognition

kaldi-asr/kaldi is the official location of the Kaldi project.

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

DeepMind's Tacotron-2 Tensorflow implementation

CTC end -to-end ASR for timit and 863 corpus.

The official repository of the Eesen project

Zero-Shot Learning with GCN (CVPR 2018)

Squeeze-and-Excitation Networks