phonemes 开源项目推荐（84 个）

zzw922cn /Automatic_Speech_Recognition

TensorFlow中Madarian和英语的端到端自动语音识别

s-macke /SAM

软件自动嘴-微型语音合成器

discordier /sam

Software Automatic Mouth - Tiny Speech Synthesizer

axelspringer /DeepPhonemizer

Grapheme to phoneme conversion with deep learning.

julianzq /deepvoice

Deep Voice: Real-time Neural Text-to-Speech

Shahabks /myprosody

A Python library for measuring the acoustic features of speech (simultaneous speech, high entropy) compared to ones of native speech.

speechio /BigCiDian

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

Halleck45 /OpenPronounce

Open-source phoneme-level English pronunciation assessment (Wav2Vec2 + DTW). Self-hosted alternative to Azure Pronunciation Assessment.

speech-industry /bournemouth-forced-aligner

Extract phoneme-level timestamps from speeh audio.

interactiveaudiolab /ppgs

High-Fidelity Neural Phonetic Posteriorgrams

rupakvignesh /Lyrics-to-Audio-Alignment

Aligns text (lyrics) with monophonic singing voice (audio). The algorithm uses structural segmentation to segment the audio into structures and then uses hidden markov models to obtain alignment within segments. The final alignment is concatenation of time stamps of lyrics within the segments for each song.

dhowe /rita

RiTa: tools for generative natural language — JavaScript, Java, and Python implementations

lake-hope /phonemes

Jason Riggle's chart of phonological features in JSON format + extras

jcsilva /multilingual-g2p

Multilingual Grapheme to Phoneme

matthijsvk /TIMITspeech

Speech recognition on the TIMIT (or any other) dataset

QUD-Technologies /quranic-phonemizer

Quranic grapheme to phoneme (G2P) converter and tajweed annotator in Hafs and Warsh

dexvdev /svelte-vrm-live

Threlte Live – 一个用于直播3D VRM虚拟形象的SvelteKit + Three.js平台。支持与谷歌生成式AI的实时聊天、ElevenLabs语音合成对口型同步、Mixamo动画和Cloudflare边缘部署——非常适合创建互动式高性能流媒体叠加。

tabahi /WebSpeechAnalyzer

JS语音分析仪，用于快速语音分析和标记

tabahi /contexless-phonemes-CUPE

pytorch model for contexless-phoneme prediction from speech audio

ReForge-Mode /UniLipSync

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