Ya-Qi Yu

D-TDNN. PyTorch implementation of Densely Connected Time Delay Neural Network

TextHawk. Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

R1-Vision. R1-Vision: Let's first take a look at the image

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

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

subtools-recipe-voxceleb. [Experimental] ASV-Subtools recipe for training D-TDNN

INTERSPEECH2020. Papers in INTERSPEECH 2020

Lens. Browse and search lenses, cameras and accessories on iPhone

ChatBot. Aggregation environment of multiple chatbots & API