AdolfVonKleist

Phonetisaurus

Phonetisaurus G2P

RnnLMG2P

Grapheme-to-Phoneme conversion with Joint-Sequence RnnLMs

SimpleLM

Simple, standalone python classes for training statistical language models using several popular smoothing methods.

AltFstAligner

An alternative OpenFst-based aligner

FSTPermuter

Compute the most likely permutation of a lattice given an LM

phonetisaurus-downloads

Models, packages and other binary files and distributions related to Phonetisaurus.

webrtc-audio-recording

This repository demonstrates how it is possible to record and playback audio in most modern browsers, and most notably - Safari 11 on both Mac and IOS.

adolfvonkleist.github.io

Docs'n'stuff

espnet

End-to-End Speech Processing Toolkit

Full-Authentication-in-Next.js

giza-kn

kaldi

This is now the official location of the Kaldi project.

packages

pyannote-algorithms

Various algorithms used all over pyannote ecosystem

python-docs-samples

Code samples used on cloud.google.com

rnn-slu

RNN for Spoken Language Understanding

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

sherpa-onnx

Real-time speech recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 servers, websocket server/client, C/C++, Python, Kotlin

soccom-d3-eg

Example using SOCCOM open source data and D3.js

ToyMinimalPerfectHash

A toy implementation of the MPH in C++

uWebSockets

Tiny WebSockets

wenet

Transformer based ASR Engine.

XAudioJS

A PCM audio stream output library that provides cross-browser compatibility.