Yeongtae

SenseVoice

Multilingual Voice Understanding Model

matmulfreellm

Implementation for MatMul-free LM.

Speech2RIR

This is the official implementation of reverberant speech to room impulse response estimator

BiRR

Binaural Room Reverb

uroman

Universal Romanizer that can convert any unicode script to roman (latin) script

superwhisper

Diff-HierVC

Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"

TTS-arxiv-daily

Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)

AI-For-Beginners

12 Weeks, 24 Lessons, AI for All!

SemantiCodec

diarizers

pyannote-metrics

A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems

speech-trident

Awesome speech/audio LLMs, representation learning, and codec models

voxconverse

Spot the conversation: speaker diarisation in the wild

VoiceCraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

TTSDatasetRecorder

A simple app for recording speech datasets.

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

yt-dlp

A feature-rich command-line audio/video downloader

dust3r

DUSt3R: Geometric 3D Vision Made Easy

metavoice-src

Foundational model for human-like, expressive TTS

DDDM-VC

Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)

ar-vits

text to speech using autoregressive transformer and VITS

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

TinySAM

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

clone-voice

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

resemble-enhance

AI powered speech denoising and enhancement

OpenVoice

Instant voice cloning by MyShell.

Automatic-Prosody-Annotator-with-SSWP-CLAP

An automatic prosodic boundary annotation tool for Text-to-Speech Synthesis (TTS).