donstang Goto Github PK

leaderboard

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.

leetcodetop

汇总各大互联网公司容易考察的高频leetcode题🔥 推荐刷题网站：https://www.lintcode.com/?utm_source=tf-github-codetop

lichee

一个多模态内容理解算法框架，其中包含数据处理、预训练模型、常见模型以及模型加速等模块。

lingvo

Lingvo

llama

Inference code for LLaMA models

lpo

Implementation of the CVPR 2015 paper: Learning to propose objects

machine-learning-yearning

Translation of <Machine Learning Yearning> by Andrew NG

masr

中文语音识别，提供预训练模型，高识别率 Chinese Speech Recognition; Mandarin Automatic Speech Recognition;

mcg

Multiscale Combinatorial Grouping - Object Proposals and Segmentation

megcc

MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器

milvus

Vector database for scalable similarity search and AI applications.

minddiffusion

A collection of diffusion models based on MindSpore

moss

An open-source tool-augmented conversational language model from Fudan University

mtan

The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR'19].

multitask-learning

多任务学习相关资料，论文，代码

nemo

NeMo: a toolkit for conversational AI

neuralnlp-neuralclassifier

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

opensmile

A github repo of the openSMILE feature extraction tool.

paddlespeech

Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

paper-reading

深度学习经典、新论文逐段精读

phonetisaurus

Phonetisaurus G2P

proxygen

A collection of C++ HTTP libraries including an easy to use HTTP server.

ptb-dataset-from-tomas-mikolov-s-webpage

py-r-fcn

R-FCN with joint training and python support

py-webrtcvad

Python interface to the WebRTC Voice Activity Detector

pychain

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

pyroomacoustics

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

r-fcn

R-FCN: Object Detection via Region-based Fully Convolutional Networks

redpajama-data-llm

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

riffusion

Stable diffusion for real-time music generation