QuentinFuxa/WhisperLiveKit
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
https://quentinfuxa.github.io/
Repositories
QuentinFuxa/Qwen3-ASR-causal
Standalone causal streaming runtime for Qwen3-ASR
QuentinFuxa/NoLanguageLeftWaiting
Simultaneous translation model for 200 languages
QuentinFuxa/PolyRAG
Agentic RAG platform purpose-built for small language models (SLM). Robust PDF/SQL search
QuentinFuxa/Alignatt4LLM
Research code for AlignAtt4LLM simultaneous speech translation.
QuentinFuxa/h_company_interview
QuentinFuxa/QuentinFuxa.github.io
Personal portfolio — applied AI engineering, open-source work, and research
QuentinFuxa/qwen3-bias-article
France unplugged Qwen for bias. An independent, preregistered audit, as a single-page article.
QuentinFuxa/SortFormer
Nemo prunned for SortFormer only
QuentinFuxa/ocrmypdf-plugin-progressbar-rest-api
OCRmyPDF + FastAPI demo: track and display OCR progress in real-time via a custom plugin.
QuentinFuxa/OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
QuentinFuxa/TopicGPT
TopicGPT allows to integrate the benefits of LLMs into Topic Modelling
QuentinFuxa/LayerLite
Recursive analysis of python stack of packages using AWS Strands Agents
QuentinFuxa/canary-mlx
NVIDIA Canary ASR model optimized for Apple Silicon using MLX.
QuentinFuxa/vllm-metal
Community maintained hardware plugin for vLLM on Apple Silicon
QuentinFuxa/iwslt-2026-baselines-1
QuentinFuxa/jupyter-mcp-headless-kit
QuentinFuxa/SimulStreaming
QuentinFuxa/QuentinFuxa
QuentinFuxa/streamlit-d3-network
Interactive D3.js network graph component for Streamlit — force-directed layout, zone clustering, multiple shapes, search, actions, i18n
QuentinFuxa/llama.cpp
LLM inference in C/C++
QuentinFuxa/CTranslate2
Fast inference engine for Transformer models
QuentinFuxa/youtube-account-switcher
QuentinFuxa/adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
QuentinFuxa/test_gcp
QuentinFuxa/convert-to-safetensors
Python utility to convert PyTorch model weights from '.bin' to '.safetensors' format.
QuentinFuxa/shap_examples
QuentinFuxa/LSTM_for_fake_news_detection
Add a way to det
QuentinFuxa/Paper-notes
QuentinFuxa/model_metric_analysis
model_metric_analysis