MARS5 speech model (TTS) from CAMB.AI

A generative speech model for daily dialogue.

🤢 LipSick: Fast, High Quality, Low Resource Lipsync Tool 🤮

PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.

Grok open release

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

End-to-end platform for building voice first multimodal agents

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

Foundational model for human-like, expressive TTS

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

Unoffical implementation of Megatts2

A ggml (C++) re-implementation of tortoise-tts

AI powered speech denoising and enhancement

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).

vits2 backbone with multilingual-bert

DLAS - A configuration-driven trainer for generative models

Reading list for research topics in Sound AI

Unsupervised Video Summarization via Successor Embeddings

Unofficial implementation of miipher

The Open Source Code of UniAudio

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

Easy-to-Use Speech MOS predictors