voidism

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

DiffCSE

Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

pywordseg

Open Source State-of-the-art Chinese Word Segmentation System with BiLSTM and ELMo. https://arxiv.org/abs/1901.05816

EAR

Code for the ACL 2023 long paper - Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering

L2KD

Code for the EMNLP2020 long paper "Lifelong Language Knowledge Distillation" https://arxiv.org/abs/2010.02123

NAR-ST

Code for the ACL-IJCNLP 2021 Findings paper "Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation"

invrat_debias

Code for "Mitigating Biases in Toxic Language Detection through Invariant Rationalization"

AWS_synthesis

mfcc_extractor

Simple one-line scripts to extract reliable MFCC features with librosa and store in HDF5 format file.

blockchain

A simple implementation of blockchain (UTXO)

ceiba-dl

NTU CEIBA 資料下載工具

ctrl

Conditional Transformer Language Model for Controllable Generation (https://einstein.ai/presentations/ctrl.pdf)

LiTy

LiTy: Listen & Type - Efficient Dictation Training Tool for English Learners.

bluebikes

BopomoBERT

End-to-end-ASR-Pytorch

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

faseAlign

Command line tool for forced-alignment of Spanish speech data

home

Personal Academic Website https://voidism.github.io/home/

homepage

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

ImpairedVoiceASR

Mandarin Speech Recognition for Impaired Voice

Insert-Delete-TextStyleTransfer

Mockingjay-Speech-Representation

Official Implementation of Mockingjay in Pytorch

myntulinebot

Recorder4ASR

Simple Record Tool for Speech Recognition

SimCSE

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

transformers-dola

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vis-lab4

voidism

Config files for my GitHub profile.

voidism.github.io

My blog <Jexus Scripts>

Zhuyin-to-ChineseWord

Auto-selecting Chinese word for Zhuyin (Bopomofo) sequence with Zhuyin level ELMo model and BiLSTM.