Search results

Llama.cpp

github.com

Llama.cpp is a GitHub repository or organization with source code, releases, documentation, or project resources.

Port of OpenAI's Whisper model in C/C++. It can be executed locally.

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

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models.

llama.cpp provides conversational AI for questions, tasks, and general assistance.

Fast inference engine for whisper in C++ using CTranslate2.

Accelerates transcription with the combination of OpenAI's Whisper Large v2, HF Transformers, Optimum, and flash attention.

Whisper API uses AI for speech, voice, transcription, music, or other audio workflows.

A Whisper CLI client compatible with the original OpenAI client, using CTranslate2 for faster inference. opensource.

bitnet.cpp

github.com

Official inference framework for 1-bit LLMs, by Microsoft. opensource.

Psst, kid, want some cheap and small LLMs?

Pure-Rust tokenizer for GGUF models, compatible with llama.cpp tokenization.

TurboPilot

github.com

A self-hosted copilot clone that uses the library behind llama.cpp to run the 6 billion parameter Salesforce Codegen model in 4 GB of RAM.

An Optimized Speech-to-Text Pipeline for the Whisper Model.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.