yuyq96

D-TDNN

PyTorch implementation of Densely Connected Time Delay Neural Network

TextHawk

Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

kaldifeat

A light-weight Python library for computing Kaldi-style acoustic features based on NumPy

pyshengyun

A Python converter for Chinese Pinyin and Shengyun (initials and finals)

INTERSPEECH2019

Papers in INTERSPEECH 2019

ICASSP2019

Papers in ICASSP 2019

ICASSP2020

Papers in ICASSP 2020

subtools-recipe-voxceleb

[Experimental] ASV-Subtools recipe for training D-TDNN

ChatBot

Aggregation environment of multiple chatbots & API

INTERSPEECH2020

Papers in INTERSPEECH 2020

Lens

Browse and search lenses, cameras and accessories on iPhone

TableCell

Image-based table cell detection: a new dataset and an improved detection method.

warp-ctc

Pytorch Bindings for warp-ctc

alluxio

Alluxio, formerly Tachyon, Unify Data at Memory Speed

asv-subtools

An Open Source Tools for Speaker Recognition

Course

Record class schedule and assignments using your iPhone

DaCiDian

DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)

fuse_bn_conv_relu

PyTorch script to fuse BatchNorm layers into succeeding Conv or Linear layers in FX graph mode

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

shanghai_house

Table-Structure-Decomposition-OCR

表格结构化和OCR（请勿商用）

TIES_DataGeneration

Dataset Generation Code for: S.R. Qasim, H. Mahmood, and F. Shafait, Rethinking Table Parsing using Graph Neural Networks (2019)

Weighted-Soft-Label-Distillation

yuyq96.github.io

A minimal Jekyll Theme to host your resume (CV)