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

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Distribute and run LLMs with a single file.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Monero: the secure, private, untraceable cryptocurrency

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

A fast, local neural text to speech system

Free Monero RandomX Miner and unified CryptoNight miner

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

An RSS/Atom feed reader for text terminals

"结巴"中文分词的C++版本

an open-source implementation of sequence-to-sequence based speech processing engine

Dooble is a scientific browser. Minimal, cute, unusually stable, and available almost everyware. Completed?

A suite of speech signal processing tools

a set of implementations of DBM

Unicode tokeniser. Ucto tokenizes text files: it separates words from punctuation, and splits sentences. It offers several other basic preprocessing steps such as changing case that you can all use…