pashanitw

llama3-and-friends-from-scratch

xeus-finetune

DictionaryByGPT4

一本 GPT4 生成的单词书📚，超过 8000 个单词分析，涵盖了词义、例句、词根词缀、变形、文化背景、记忆技巧和小故事

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

AudioNotes

快速提取音视频内容，整理成一份结构化的markdown笔记

auto-prompt-engineering

avatar

AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (https://arxiv.org/abs/2406.11200)

ControlSpeech

ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec

CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

dataspeech

DiffSynth-Studio

Enjoy the magic of Diffusion models!

FlashSpeech

FlashSpeech: Efficient Zero-Shot Speech Synthesis

GPT-Talker

Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)

Kolors

Kolors Team

LivePortrait

Bring portraits to life!

llamacoder

Open source Claude Artifacts – built with Llama 3.1 405B

mini-omni

open-source multimodel large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

my-website

Driven by nextjs, shadcnui style blog template.

parler-tts

Inference and training library for high-quality TTS models.

react-chatbotify

A modern React library for creating flexible and extensible chatbots.

SSR-Speech

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

StableTTS

Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3

ttts

Train the next generation of TTS systems.

ultravox

VITS-Plus

WebDesignAgent

An agent used for webdesign

Whisper-Finetune

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

index-tts

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

LLaSA_training

LLaSA: Scaling Train-time and Test-time Compute for LLaMA-based Speech Synthesis

Zonos