Igor Tavčar's repositories
autogen
A programming framework for agentic AI. Join our Discord: https://aka.ms/autogen-dc
ChatDev
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
classla
CLASSLA Fork of the Official Stanford NLP Python Library for Many Human Languages
classla_lab
A lab environment focused on benchmarking & profiling Classla NLP pipelines.
ColossalAI
Making big AI models cheaper, easier, and more scalable
convertvec
Convert word2vec vectors between binary and plain text format
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
faster-whisper
Faster Whisper transcription with CTranslate2
GlitchLabel
G..lit...c...hing UILa..bel fo..r iO...S :tv:
GPT2
PyTorch Implementation of OpenAI GPT-2
hyperaudio-lite
Hyperaudio Lite - a Super-lightweight Interactive Transcript Player
hyperaudio-lite-editor
A lightweight transcript editor for editing and correcting STT generated timed transcripts
lila
♞ lichess.org: the forever free, adless and open source chess server ♞
LLMFarm
llama and other large language models on iOS and MacOS offline using GGML library.
llmfarm_core.swift
Swift library to work with llama and other large language models.
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
mptools
Wrapper for multiprocessing that provides a bunch of boilerplate.
netty-socketio
Socket.IO server implemented on Java. Realtime java framework
Stockfish-1
UCI chess engine
takeoff-community
TitanML Takeoff Server is an optimization, compression and deployment platform that makes state of the art machine learning models accessible to everyone.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation
whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)