Yihui Fu's repositories
2021-ISMIR-MSS-Challenge-CWS-PResUNet
Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.
aps
A workspace for single/multi-channel speech recognition & enhancement & separation.
Bilibili_Spider_by_UserID
Python 爬取B站UP主的所有视频链接及详细信息
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
deepvqe
An unofficial implementation of DeepVQE proposed by Microsoft Corp.
felixfuyihui
Config files for my GitHub profile.
FunClip
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
G722Codec
G722格式音频编解码
g722enc
G722 and G722.1 file encoders for FreeSWITCH
setk
Tools for Speech Enhancement integrated with Kaldi
SLAM-LLM
Speech, Language, Audio, Music Processing with Large Language Model
speech-trident
Awesome speech/audio LLMs, representation learning, and codec models
Tang
泡面哥汤达人的前世今生，从默默无闻到人人喊打【截止到2019年12月9日】
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
youtube-dl
Command-line program to download videos from YouTube.com and other video sites