Minimalist ML framework for Rust

live transcription in Rust

Compiler from OCaml to Javascript.

Python client for the Gradium Voice AI api.

Make text LLMs listen and speak

Googles NotebookLM but local

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

Voracious radix sort

A collection of optimisers for use with candle

Rust client for the Gradium Voice

R Interface to Torch

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

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.

A small rust-based data loader

protein utilities in Rust

Rust bindings for the C++ api of PyTorch.

Simple and efficient time representation in Rust.

Experimental compiler for deep learning models

Fine-tuning Moshi/J-Moshi on your own spoken dialogue data

python bindings for symphonia/opus - read various audio formats from python and write opus files

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

A Fish Speech implementation in Rust, with Candle.rs

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

A voice chat app

Simple high-throughput inference library

Low rank adaptation (LoRA) for Candle.