MXuer's repositories
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Kindle_download_helper
Download all your kindle books script.
draw-e2e-arch
端到端语音识别模型的结构图
alpaca-lora
Instruct-tune LLaMA on consumer hardware
mms-alignment-tools
using MMS to do the audio-transcript alignment
notesbooks
日常工作中用到的一些小的活,用jupyter notebook干的
whisper-eval
用Whisper不同的模型,在不同语种、不同测试集上的效果。
books-notes
一些读书笔记
asr-notes-e2e
端到端语音识别相关的一些笔记
notes-for-notes
记一些笔记。
FreeVC
FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion
Wav2Lip
This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.
reading-paper-notes
notes for paper reading
mini-asr
code practice for asr models including las, ctc, rnn-t and others.
asr-work-mini
For my son, do asr and nlu annotation works.
git-flight-rules
Flight rules for git
lhotse
Tools for handling speech data in machine learning projects.
inaSpeechSegmenter
CNN-based audio segmentation toolkit. Allows to detect speech, music and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
speech-recognition-papers
Towards hot directions in industrial speech recognition
chinese-asr-kaldi-and-other
Start now, first build a model for chinese from commonvoice, then use keras to build end2end model, keep updating
pinyin-data
汉字拼音数据
keras-resources
Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library
codes
learning codes for python, C++, and speech recognition
awesome-kaldi
This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )
language-recognition
CNN to classify samples of voice recordings into the language that was spoken