Pinned Repositories
3D_GAN_Lung_Nodules
GAN code for generating lung nodule ct scans
3DUSCT-data-access-script
3DUSCT data access example script and visualization
AI_Project
AI專案開發筆記
audio_transcription_app_version_2
A simple audio transcription app with Gradio and Whisper
brain2music
A Python and SD pipeline to convert EEG data to music in real time
XCAWAStickerMaker
A WhatsApp Sticker Maker iOS App with Vision API Subject Lifting / Background Removal
newsiquare's Repositories
newsiquare/XCAWAStickerMaker
A WhatsApp Sticker Maker iOS App with Vision API Subject Lifting / Background Removal
newsiquare/brain2music
A Python and SD pipeline to convert EEG data to music in real time
newsiquare/chacha-chatbot
newsiquare/ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
newsiquare/Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
newsiquare/ChuanhuChatGPT
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
newsiquare/deepspeed_code
newsiquare/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
newsiquare/folotoy-server-self-hosting
Config files for self-hosting the FoloToy Server. Documents: https://docs.folotoy.com
newsiquare/freecbt
✨🐙 A GPL Licensed Cognitive Behavioral Therapy app for iOS and Android
newsiquare/GPT-Linebot-python-flask-on-vercel
GPT-Linebot using python flask for vercel
newsiquare/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
newsiquare/InstantStyle
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥
newsiquare/kohya_ss
newsiquare/llama-factory-docker
newsiquare/llamafile
Distribute and run LLMs with a single file.
newsiquare/llm_course_20231228
newsiquare/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
newsiquare/open-webui
ChatGPT-Style WebUI for Ollama (Formerly Ollama WebUI)
newsiquare/privateGPT
Interact with your documents using the power of GPT, 100% privately, no data leaks
newsiquare/QuickAgent
newsiquare/realtime-conversation-copilot
newsiquare/speech-to-text
Real-time transcription using faster-whisper
newsiquare/UnitySpeechToText
A native Unity plugin to convert speech to text on Android & iOS
newsiquare/unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
newsiquare/whisper-diarization
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
newsiquare/whisper.cpp
Port of OpenAI's Whisper model in C/C++
newsiquare/XCAAiAssistant
GPT4 Voice Assistant SwiftUI App
newsiquare/XCAOpenAIClient
OpenAI Swift Client Generated from OpenAI OpenAPI YML
newsiquare/ZRVoiceGPT
Tutorial voice gpt