fantasyyyy Goto Github PK

aidatatang_200zh

Aidatatang_200zh is an open source Chinese Mandarin speech corpus released by DataTang Technology Co., Ltd (www.datatang.com).

chinese-bert-wwm

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

chinese-electra

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

crepe

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

f

fastspeech2

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

forced-alignment-tools

A collection of links and notes on forced alignment tools

img-encode

Encode an image to sound and view it as a spectrogram - turn your images into music

lyrics-to-audio-alignment

Aligns text (lyrics) with monophonic singing voice (audio). The algorithm uses structural segmentation to segment the audio into structures and then uses hidden markov models to obtain alignment within segments. The final alignment is concatenation of time stamps of lyrics within the segments for each song.

mcd

Mel cepstral distortion (MCD) computations in python.

montreal-forced-aligner

Command line utility for forced alignment using Kaldi

mosnet

Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

music-source-separation

Deep neural networks for separating singing voice from music written in TensorFlow

musiclyricchatbot

chatbot based on music region using method including es and music kb.基于14W歌曲知识库的问答尝试，功能包括歌词接龙，已知歌词找歌曲以及歌曲歌手歌词三角关系的问答。

nisqa

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

p2fa_py3

Penn Phonetics Lab Forced Aligner Toolkit (P2FA) for Python3

speech_separation

Include some core functions and model to handle speech separation

spleeter

Deezer source separation library including pretrained models.

tensorflow

Computation using data flow graphs for scalable machine learning

tts-clone-chinese

基于Real-Time-Voice-Cloning语音克隆中文普通话实现