v3ucn / llama3-txt2json-dataset-makerLinks
文本语料转训练集工具，txt转dataset
☆93Updated last year
Alternatives and similar repositories for llama3-txt2json-dataset-maker
Users that are interested in llama3-txt2json-dataset-maker are comparing it to the libraries listed below
Sorting:
- Sample GLM4V + ChatTTS AI assistant☆85Updated last year
- generate ppt with llm☆101Updated last year
- GraphRAG-Ollama-UI + GraphRAG4OpenWebUI 融合版（有gradio webui配置生成RAG索引，有fastapi提供RAG API服务）☆107Updated last year
- 10000 chatTTS voices ！chatTTS 音色库，再也不为音色抽卡烦恼啦。这是我第一个项目，熬夜龟速生产10000条音色并上传Github，给点鼓励呗哈！主域名：https://www.TTSlist.com 备用：http://ttslist.aiqb…☆191Updated last year
- Phi3 中文后训练模型仓库☆322Updated 9 months ago
- Unsloth框架在Windows平台微调训练Qwen2大模型，非WSL☆61Updated last year
- 一个用于CosyVoice的api接口项目☆309Updated 2 weeks ago
- ChatTTS HTTP API☆55Updated last year
- 实时STT，连接OpenAI接口/智谱AI（流式LLM）和GPT-SOVITS/Edge-TTS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果☆415Updated 8 months ago
- 使用 FastAPI、Streamlit本地部署ChatTTS文本转语音模型，并通过 Docker Compose 进行容器化部署。☆27Updated 11 months ago
- Easegen is an open-source digital human course creation platform offering comprehensive solutions from course production and video manage…☆242Updated 4 months ago
- ☆180Updated 7 months ago
- 从小说中提取对话数据集☆242Updated last year
- 基于Linly-Talker数字人改版的教育系统，包含网课总结、数字人对话、Chatbot对话，项目可在autodl部署☆32Updated last year
- ☆44Updated 2 years ago
- VideoFinder is an advanced video analysis tool powered by multimodal AI, designed to help users easily locate and identify specific objec…☆162Updated 10 months ago
- ☆58Updated 10 months ago
- GOT-OCR的GUI版本，提供OCR、导出PDF、批处理等功能，但不提供训练功能☆179Updated 2 months ago
- 在DH_live项目基础上修改，添加webui界面☆66Updated 4 months ago
- 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☆168Updated 10 months ago
- ChatPPT is powered by chatgpt/ollama, it could help you to generate PPT/slide. It supports output in English and Chinese☆295Updated 3 months ago
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆105Updated last year
- Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。☆295Updated last year
- 基于通义千问 Qwen2.5-Omni 的实时语音对话系统，使用在线API服务，支持实时语音交互、动态语音活动检测和流式音频处理。A real-time voice conversation system based on Qwen2.5-Omni Online-API, …☆65Updated 4 months ago
- ☆351Updated last year
- 基于 faster-whisper 的伪实时语音转写服务☆226Updated 4 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆170Updated 7 months ago
- 阿里SenseVoice的fastpi封装，采用onnx发布，体积更小，附带量化模型，支持GPU。支持从URL文件进行语音识别。☆99Updated last year
- virtualwife-llm-factory 是一个llm训练框架，用于解决虚拟角色训练入门门槛高的问题，该框架具备自动生成语料，性格塑造评估，基于国产llm微调训练等核心能力，目前还在开发，可以点个star~ 关注一下☆51Updated 3 months ago
- 基于OpenVoice和Melotts整合的中文版webui，添加resemble_enhance音频增强功能☆96Updated last year