ChatTTS
2noise/ChatTTS
Conversational Chinese and English speech generation with speaker and prosody controls; released model weights are noncommercial.
ToolAI.io · GitHub چینل
GitHub پر حال ہی میں شامل کیے گئے اوپن سورس AI پروجیکٹس دریافت کریں، جن کے ساتھ ریپوزٹری کی معلومات، سیٹ اپ نوٹس، لائسنس اور متعلقہ وسائل بھی موجود ہیں۔
عوامی ریپوزٹری کا ڈیٹا
2noise/ChatTTS
Conversational Chinese and English speech generation with speaker and prosody controls; released model weights are noncommercial.
google-ai-edge/mediapipe
On-device ML libraries, models, and tools for vision, text, and audio across supported platforms.
TencentARC/GFPGAN
Face restoration using generative facial priors, with optional background enhancement in an image-restoration workflow.
JaidedAI/EasyOCR
A Python/PyTorch OCR library returning text regions, recognized strings, and confidence values.
naptha/tesseract.js
Tesseract OCR for browsers and Node.js using WebAssembly, suitable for image-to-text features in JavaScript apps.
photoprism/photoprism
A self-hostable photo and video library with automatic labels, face organization, and metadata search.
CopilotKit/CopilotKit
An SDK connecting applications and agents through shared state, chat, generative UI, and human input.
gradio-app/gradio
Build interactive model demos and tools from Python functions with text, image, audio, and custom layouts.
paperless-ngx/paperless-ngx
A self-hosted document archive combining OCR, search, and metadata organization for scanned and digital files.
labring/FastGPT
A visual knowledge-workflow platform with document ingestion, hybrid retrieval, reranking, and application publishing.
onyx-dot-app/onyx
A self-hostable team AI platform combining knowledge connectors, retrieval, agents, and research workflows.
microsoft/graphrag
A graph-based text indexing and question-answering research project, now largely in maintenance mode.
صفحہ 4 / 26 · 305 پروجیکٹس