phoneme 开源项目推荐（62 个）

tiberiu44 /TTS-Cube

End-2-end speech synthesis with recurrent neural networks

ZDisket /TensorVox

Desktop application for neural speech synthesis written in C++

maxrmorrison /pyfoal

Python forced alignment

magicus /phoneME

The archived source code of the old Sun phoneME project, converted to git

ftyers /commonvoice-utils

Linguistic processing for Common Voice

orenskl /pico-jvm

A small Java virtual machine for Raspberry Pi Pico. This is based on the CLDC Profile for embedded devices.

nyrahealth /nyra-forced-aligner

Word and phoneme level speech timing for spontanoues speech. Fast, accurate and robust.

timedomain-tech /ACE_phonemes

a guide to grapheme-to-phoneme conversion and phoneme list for ace singing voice synthesis engine

team-telnyx /medical-pronunciation-dictionary

Prepackaged medical pronunciation dictionary for voice AI TTS engines. 960+ drug names, clinical terms, anatomical terms, and medical acronyms with phonetic aliases. Works with Telnyx, ElevenLabs, Vapi, Retell, and Amazon Polly.

Wikidepia /g2p-id

Indonesian Grapheme-to-Phoneme (IPA notation)

ReForge-Mode /UniLipSync

Load your phoneme files and generate the lipsync animation from your recorded audio files. No video or webcam needed!

ronggong /jingjuSingingPhraseMatching

Code for the paper: Audio to Score Matching by Combining Phonetic and Duration Information

OpenFaceFX /OpenFaceFX

Open-source lip-sync in the spirit of FaceFX: audio + transcript → viseme animation curves for any engine. MIT, numpy-only.

maxrmorrison /pypar

Phoneme alignment representation compatible with multiple forced aligners

ronggong /EUSIPCO2017

The phoneme classification code for EUSIPCO 2017 paper: Timbre Analysis of Music Audio Signals with Convolutional Neural Networks

MysteryPancake /Phomeme

Simple sentence mixing tool (work in progress)

team-pp-studio /VoiceTuber

VTuber application which only requires your voice and microphone, no need for a webcam or other tracking nonsense.

greg-kennedy /p5-NRL-TextToPhoneme

Perl implementation of the Naval Research Laboratory text-to-phoneme algorithm, described by Elovitz et al (1976)

swshon /dialectID_siam

Dialect identification using Siamese network

traderpedroso /xphoneBR

XphoneBR is a Brazilian portuguese transformer base grapheme-to-phoneme and normalization tool modeling library that leverages recent deep learning technology and is optimized for usage in production systems such as TTS. In particular, the library should be accurate, fast, easy to use