pkufool

simple-wer

A simple command line tool to calculate WER for ASR.

open-commands

cppinyin

Converting Chinese sentences into pinyin sequences, implemented in C++, very fast and easy to deploy.

icefall

k2

FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar

keyword-spotting-models

simple-sentencepiece

A simple sentencepiece encoder and decoder

text_search

Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup

cpp_neon_play

A cpp arm neon playground for beginners.

fast_rnnt

A torch implementation of a recursion which turns out to be useful for RNN-T.

open-speech

sherpa

Streaming and non-streaming ASR server in Python

sherpa-onnx

Speech recognition with sherpa-onnx (without depending on PyTorch)

simple-search

clash-for-linux-backup

Linux最完整的Clash for Linux的备份仓库，完全可以使用！由Yizuko进行修复及维护

dev_tools

diagnostics

images

k2-fsa-www

Source for web page, to be used for distribution of whl files etc.

KTokenizer

lexicon

A general lexicon for phone, pinyin and byte-pair-encoding.

lhotse

libriheavy

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

nginx-theme

The theme for nginx fancyindex

pkufool.github.io

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, etc.

sherpa-test-data

simple-image

简单的图床程序

V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.