v3ucn

星球号:31340195

China

Pinned Repositories

ASR_TOOLS_SenseVoice_WebUI
Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型
Language:Python173 4 722
Causallm14b_llama_webui_adult_version
Causallm14b大模型量化版本,基于DPO算法改进,无内容审查,无思想钢印,百无禁忌Webui
Language:Python193 4 626
CosyVoice_for_MacOs
CosyVoice在苹果MacOs上使用的版本
Language:Python122 3 917
CosyVoice_For_Windows
CosyVoice在Windows环境下使用的版本
Language:Python648 5 4496
GPT-SoVITS-V2
GPT-SoVITS-V2模型，合并了官方的一些PR，包含但不限于:参考音频自动填充，字幕同步，SillyTavern酒馆接入等功能
Language:Python134 3 918
live2d-TTS-LLM-GPT-SoVITS-Vtuber
低成本的简单基于live2d TTS文字转语音和大模型聊天的直播解决方案
Language:HTML243 1 837
llama3-txt2json-dataset-maker
文本语料转训练集工具，txt转dataset
Language:Python91 2 017
Modelscope_Faster_Whisper_Multi_Subtitle
基于Faster-whisper和modelscope一键生成双语字幕，双语字幕生成器,基于离线大模型,Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model
Language:Python373 5 1947
OpenVoiceV2_Webui_resemble_enhance
基于OpenVoice和Melotts整合的中文版webui，添加resemble_enhance音频增强功能
Language:Python91 1 320
Python_ChatGPT_ForDingding_OpenAi
基于Python3.10的OpenAI聊天机器人ChatGPT模型接入钉钉Dingding机器人单聊/群聊功能
Language:Python63 5 222

v3ucn's Repositories

v3ucn/CosyVoice_For_Windows
CosyVoice在Windows环境下使用的版本
Language:Python648 5 4496
v3ucn/Modelscope_Faster_Whisper_Multi_Subtitle
基于Faster-whisper和modelscope一键生成双语字幕，双语字幕生成器,基于离线大模型,Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model
Language:Python373 5 1947
v3ucn/GPT-SoVITS-V2
GPT-SoVITS-V2模型，合并了官方的一些PR，包含但不限于:参考音频自动填充，字幕同步，SillyTavern酒馆接入等功能
Language:Python134 3 918
v3ucn/CosyVoice_for_MacOs
CosyVoice在苹果MacOs上使用的版本
Language:Python122 3 917
v3ucn/DH_live_webui
在DH_live项目基础上修改，添加webui界面
Language:JavaScript569
v3ucn/DH_live
每个人都能用的数字人
Language:Python6 0 0
v3ucn/digital_human_video_player
洛曦数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频
Language:Python3 0 0
v3ucn/Fast-Spark-TTS
基于SparkTTS模型，提供高质量中文语音合成与声音克隆服务。
3
v3ucn/fish-speech
Brand new TTS solution
Language:Python3 0 0
v3ucn/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Language:Python3 0 02
v3ucn/bailing
百聆是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断
2
v3ucn/Bert-VITS2-FixBug
Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。
Language:Python2 0 01
v3ucn/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Language:Python2 0 0
v3ucn/F5-TTS
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
2
v3ucn/oh-my-live2d
应用于浏览器环境且开箱即用的Live2D组件, 它支持所有版本的Live2D模型, 使用方式足够简单并且高可自定义, 可以快速为您的个人网站添加Live2D看板娘, 使您的个人网站变得更具有特色.
2
v3ucn/SillyTavern
LLM Frontend for Power Users.
Language:JavaScript2 0 0
v3ucn/Ultralight-Digital-Human
一个超轻量级、可以在移动端实时运行的数字人模型
2
v3ucn/StableTTS
Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
1
v3ucn/Step-Audio-tts
1
v3ucn/EDTalk
[ECCV 2024 Oral] EDTalk - Official PyTorch Implementation
Language:Python0 0
v3ucn/espeakng-loader
This package loads the espeak-ng shared library so it will be available for other libraries.
v3ucn/HeyGem-Linux-Python-Hack
A docker free offline version for HeyGem; Python and Linux is all you need!
v3ucn/IMAGDressing
👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing
Language:Python0 0
v3ucn/LatentSync
Taming Stable Diffusion for Lip Sync!
v3ucn/LivePortrait
Bring portraits to life!
Language:Python0 0
v3ucn/local-llasa-tts-windows
Examples of using the llasa-tts models locally
v3ucn/MeloTTS-ONNX
An implementation of MeloTTS by onnxruntime
v3ucn/open-neruosama
v3ucn/seed-vc
zero-shot voice conversion with in context learning
Language:Python0 01
v3ucn/Spark-TTS
Spark-TTS Inference Code