主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Speech, Language, Audio, Music Processing with Large Language Model

AirLLM 70B inference with single 4GB GPU

Retrieval and Retrieval-augmented LLMs

Benchmarking library for RAG

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

the resources about the application based on LLM with RAG pattern

Named Entity Correctior for ASR system.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Enhancing Translation with RAG-Powered Large Language Models

Whisper realtime streaming for long speech-to-text transcription and translation

Transcription, forced alignment, and audio indexing with OpenAI's Whisper

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

✨✨Latest Advances on Multimodal Large Language Models

speaker adaptation, ASR, personality

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

An awesome spoken LID repository. (Working in progress

Faster distil-whisper transcription with CTranslate2

语音方向实验室/公司/资源/实习等，欢迎推荐或自荐

Speech recognition module for Python, supporting several engines and APIs, online and offline.

ESPnet Model Zoo

Repository for SLURP paper

Notebooks and various random fun

[ICASSP 2022] Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection

open-source Mandarian biased word dataset

Some Conferences' accepted paper lists (including AI, ML, Robotic)