A command-line application to convert images, PDFs, and audio files to text using Apple's APIs

experiments with inference on llama

AudioLDM: Generate speech, sound effects, music and beyond, with text.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

GGUF implementation in C as a library and a tools CLI program

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

GPU accelerated client-side embeddings for vector search, RAG etc.

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

100% Local AGI with LocalAI

✔️Contextual word checker for better suggestions

SQLite3 bindings for Node.js

Data extraction with LLM on CPU

Disque ported as Redis module

Disque is a distributed message broker

Framework for benchmarking vector search engines

A simple Prolog Interpreter written in a few lines of Python 3. It runs a limited subset of Prolog and uses backtracking and generators in order to perform its magic.

JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT-2 / GPT-3 / GPT-4. Port of OpenAI's tiktoken with additional features.

Cross-Platform, GPU Accelerated Whisper 🏎️

A high-throughput and memory-efficient inference and serving engine for LLMs

Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon

ULID generator for NodeJS and the browser

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

The code for the bark-voicecloning model. Training and inference.

Fast Text Classification with Compressors dictionary

Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

fast vector database made in numpy

one-click face swap