Repositories list

• TokenFormer

  Public
  Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

  Python

  •

  Apache License 2.0

  •19•0•0•0•Updated Nov 12, 2024Nov 12, 2024

• Theraxus-speech-to-speech

  Public
  Theraxus AI: A modular conversational AI platform ⚙️ blending STT 🎙️, TTS 🗣️, and RAG 📚 for seamless, context-aware dialogues and human-like interactions 🤖💬

  Python

  •

  Apache License 2.0

  •4•0•0•0•Updated Nov 9, 2024Nov 9, 2024

• OuteTTS

  Public
  Python

  •

  Apache License 2.0

  •23•0•0•0•Updated Nov 5, 2024Nov 5, 2024

• Medical-Graph-RAG

  Public
  Medical Graph RAG: Graph RAG for the Medical Data

  Python

  •

  MIT License

  •36•0•0•0•Updated Oct 25, 2024Oct 25, 2024

• BitNet-1bit-inference-for-LLM

  Public
  Official inference framework for 1-bit LLMs

  C++

  •

  MIT License

  •757•0•0•0•Updated Oct 18, 2024Oct 18, 2024

• swarm-Multi-agent-orchestration

  Public
  Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

  Python

  •

  MIT License

  •1.6k•0•0•0•Updated Oct 12, 2024Oct 12, 2024

• fstalign

  Public
  An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.

  C++

  •

  Apache License 2.0

  •8•0•0•0•Updated Sep 24, 2024Sep 24, 2024

• moshi

  Public
  Python

  •

  Apache License 2.0

  •525•0•0•0•Updated Sep 18, 2024Sep 18, 2024

• GOT-OCR2.0

  Public
  Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

  Python

  •514•0•0•0•Updated Sep 11, 2024Sep 11, 2024

• Nvidia-NeMo

  Public template
  A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

  Python

  •

  Apache License 2.0

  •2.5k•0•0•0•Updated Sep 5, 2024Sep 5, 2024

• directus

  Public
  The Modern Data Stack 🐰 — Directus is an instant REST+GraphQL API and intuitive no-code data collaboration app for any SQL database.

  TypeScript

  •

  Other

  •3.9k•0•0•0•Updated Sep 2, 2024Sep 2, 2024

• directus-extension-disable-listing

  Public
  Directus custom extension to disable listing

  TypeScript

  •

  GNU General Public License v3.0

  •4•0•0•0•Updated Aug 31, 2024Aug 31, 2024

• graphrag

  Public
  A modular graph-based Retrieval-Augmented Generation (RAG) system

  Python

  •

  MIT License

  •1.9k•0•0•0•Updated Aug 26, 2024Aug 26, 2024

• speech-to-speech

  Public template
  Speech To Speech: an effort for an open-sourced and modular GPT4-o

  Python

  •

  Apache License 2.0

  •367•0•0•0•Updated Aug 26, 2024Aug 26, 2024

• directus-extension-flow-manager

  Public
  A directus custom module extension for managing directus flow includes backup/restore, duplication and grouping the flow.

  Vue

  •

  GNU General Public License v3.0

  •6•0•0•0•Updated Aug 25, 2024Aug 25, 2024

• agentic-customer-service-medical-clinic

  Public
  This software contains an agent based on LangGraph & LangChain for solving general requests in the Whatsapp channel of this medical clinic

  Python

  •29•0•0•0•Updated Aug 14, 2024Aug 14, 2024

• Qwen2-Audio

  Public
  The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

  Python

  •82•0•0•0•Updated Aug 12, 2024Aug 12, 2024

• langgraph-studio

  Public
  Desktop app for prototyping and debugging LangGraph applications locally.

  128•0•0•0•Updated Aug 6, 2024Aug 6, 2024

• cancer-trial-match

  Public
  Derive data for cancer clinical trials, plus web viewer to visualise results

  HTML

  •

  GNU General Public License v3.0

  •2•0•0•0•Updated Jul 26, 2024Jul 26, 2024

• guidance

  Public
  A guidance language for controlling large language models.

  Jupyter Notebook

  •

  MIT License

  •1k•0•0•0•Updated Jul 24, 2024Jul 24, 2024

• SpanMarkerNER

  Public
  SpanMarker for Named Entity Recognition

  Jupyter Notebook

  •

  Apache License 2.0

  •28•0•0•0•Updated Jul 24, 2024Jul 24, 2024

• coqui-ai-TTS-up-to-date

  Public template
  🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

  Python

  •

  Mozilla Public License 2.0

  •4.3k•0•0•0•Updated Jul 18, 2024Jul 18, 2024

• ai-renamer

  Public
  A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

  JavaScript

  •

  GNU General Public License v3.0

  •98•0•0•0•Updated Jul 14, 2024Jul 14, 2024

• parler-tts

  Public
  Inference and training library for high-quality TTS models.

  Python

  •

  Apache License 2.0

  •471•0•0•0•Updated Jul 11, 2024Jul 11, 2024

• bark

  Public
  🔊 Text-Prompted Generative Audio Model

  Jupyter Notebook

  •

  MIT License

  •4.3k•0•0•0•Updated Jul 10, 2024Jul 10, 2024

• fast-whisper-finetuning

  Public
  Jupyter Notebook

  •37•0•0•0•Updated Jul 10, 2024Jul 10, 2024

• TTS-Coqui

  Public
  🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

  Python

  •

  Mozilla Public License 2.0

  •4.3k•0•0•0•Updated Jul 8, 2024Jul 8, 2024

• distil-whisper

  Public
  Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

  Python

  •

  MIT License

  •294•0•0•0•Updated Jul 8, 2024Jul 8, 2024

• dataspeech

  Public
  Python

  •

  MIT License

  •46•0•0•0•Updated Jul 5, 2024Jul 5, 2024

• orphapacket

  Public
  3•0•0•0•Updated Jul 3, 2024Jul 3, 2024