Minimalist ML framework for Rust

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.

Swift for TensorFlow

Rust bindings for the C++ api of PyTorch.

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Instant, controllable, local pre-trained AI models in Rust

Convolutional neural network model for video classification trained on the Kinetics dataset.

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…

A voice chat app

Compiler from OCaml to Javascript.

The Swift Programming Language

Make text LLMs listen and speak

An implementation of the diffusers api in Rust

R Interface to Torch

OCaml bindings for PyTorch

Googles NotebookLM but local

Tutorial for Porting PyTorch Transformer Models to Candle (Rust)

Rust wrapper for Microsoft's ONNX Runtime (version 1.8)

LLM Orchestrator built in Rust

J-Moshi: A Japanese Full-duplex Spoken Dialogue System

A fully in-browser privacy solution to make Conversational AI privacy-friendly

Kyutai with an "eye"

Low rank adaptation (LoRA) for Candle.

根据文本描述搜索本地图片的工具，powered by Rust + candle + CLIP

An LLM interface (chat bot) implemented in pure Rust using HuggingFace/Candle over Axum Websockets, an SQLite Database, and a Leptos (Wasm) frontend packaged with Tauri!

Simple high-throughput inference library