Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus

A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.

🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data

Fast and accurate automatic speech recognition (ASR) for edge devices

Real-time text-to-speech with Qwen3-TTS

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Rust client for the Gradium Voice

Python client for the Gradium Voice AI api.

A real-time and multilingual speech translation model

Fully local, private and cross platform Speech-to-Text with LLM Post-processing

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Port of OpenAI's Whisper model in C/C++

Build local voice agents with open-source models

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Geometry processing and machine learning with functional maps.

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

LogAI - An open-source library for log analytics and intelligence

Reference PyTorch implementation and models for DINOv3

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Supercharge Your LLM Application Evaluations 🚀

A Tutorial for Setting Python Development Environment with VScode and Docker

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

Probabilistic time series modeling in Python

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

Run frontier AI locally.

This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter multilingual chat model based on BLOOM.

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

🧱 Modula software package