LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Self-Supervised Speech Pre-training and Representation Learning Toolkit

End-to-end ASR/LM implementation with pytorch.

Event-driven network library for multi-threaded Linux server in C++11

PyTorch implementation of LF-MMI for End-to-end ASR

it's a train acoustics model code lib

Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)

A fast parallel implementation of RNN Transducer.

Papers with code. Sorted by stars. Updated weekly.

Build an attention-based model for speech recogntion.Use the Word2vec model to help to train the attention model.

Learn regex the easy way

Deep Xi: A Deep Learning Approach to A Priori SNR Estimation. Used for Speech Enhancement and robust ASR.

Yet another speech toolkit based on Kaldi and PyTorch

An open-source speech separation and enhancement library

transform-average-concatenate (TAC) method for end-to-end microphone permutation and number invariant ad-hoc beamforming.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Source code for the paper <Bridging the Gap between Training and Inference for Neural Machine Translation>

Implement [Wave-U-Net](https://arxiv.org/abs/1806.03185) by PyTorch, and migrate it to the speech enhancement area.

Audio fingerprinting and recognition in Python

Implement A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement by PyTorch.

An open-source big data platform designed and optimized for the Internet of Things (IoT).

Tool-box for efficient build and debug in Python. Especially for Scientific Computing and Computer Vision.

LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)

Deep neural network based speech enhancement toolkit

A two-stage polyphonic sound event detection and localization method for both SED and DOA.

Problem Agnostic Speech Encoder