NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Go ahead and axolotl questions

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Ongoing research training transformer models at scale

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Fast and memory-efficient exact attention

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

The agent engineering platform

한국어 음성인식 STT API 리스트. 각 성능 벤치마크.

Foundational Models for State-of-the-Art Speech and Text Translation

Train transformer language models with reinforcement learning.

unofficial vits2-TTS implementation in pytorch

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Inference code for Llama models

This repo is for Korean wiki table question answering datasets described in the paper of Korean-Specific Dataset for Table Question Answering

KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model to understand Korean instructions)

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Polyglot: Large Language Models of Well-balanced Competence in Multi-languages

Overview and tutorial of the LangChain Library

The official GitHub page for the survey paper "A Survey of Large Language Models".

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

한국어 음성인식 튜토리얼

An integrated library for Korean language preprocessing.

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

AI on the way. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.

Flexible components pairing 🤗 Transformers with ⚡ Pytorch Lightning