MXuer

asr-notes

平时学习工作的笔记

asr-work-mini

For my son, do asr and nlu annotation works.

chinese-asr-kaldi-and-other

Start now, first build a model for chinese from commonvoice, then use keras to build end2end model, keep updating

alpaca-lora

Instruct-tune LLaMA on consumer hardware

asr-notes-e2e

端到端语音识别相关的一些笔记

awesome-kaldi

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

mms-alignment-tools

using MMS to do the audio-transcript alignment

books-notes

一些读书笔记

codes

learning codes for python, C++, and speech recognition

documents_llama

draw-e2e-arch

端到端语音识别模型的结构图

Federated-learning-ASR

FreeVC

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

git-flight-rules

Flight rules for git

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.

keras-resources

Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library

Kindle_download_helper

Download all your kindle books script.

language-recognition

CNN to classify samples of voice recordings into the language that was spoken

lhotse

Tools for handling speech data in machine learning projects.

mini-asr

code practice for asr models including las, ctc, rnn-t and others.

notes-for-notes

记一些笔记。

notesbooks

日常工作中用到的一些小的活，用jupyter notebook干的

pinyin-data

汉字拼音数据

reading-paper-notes

notes for paper reading

sft_datacollections

speech-recognition-papers

Towards hot directions in industrial speech recognition

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.

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

whisper-asr-finetune

whisper-eval

用Whisper不同的模型，在不同语种、不同测试集上的效果。