Thamme Gowda

nllb-serve. Meta's "No Language Left Behind" models served as web app and REST API

mtdata. A tool that locates, downloads, and extracts machine translation corpora

tensorflow-grpc-java. Tensorflow grpc java client for image recognition serving inception model

charliebot. The ALICE/ALICEBOT/CHARLIE/CHARLIEBOT

tika-dl4j-spark-imgrec. Image recognition on Spark cluster powered by Deeplearning4j and Apache Tika

tika-ner-corenlp. Stanford CoreNLP NER addon for Apache Tika's NamerEntityParser

006-many-to-eng. Machine translation of many to English

005-nmt-imbalance. Finding the Optimal Vocabulary for NMT

solr-similarity. Finding similarity of documents by making use of vector space model

autoextractor. A toolkit for clustering web pages based on various similarity measures.

ML101. Machine learning crash course for absolute beginners.

awkg. awkg is an awk-like text-processing tool powered by python language

notes. A place to dump all my homeworks and practice scribblings.

virtchar. A Dialog toolkit for making favorite TV characters as chatbots

parser-indexer. Metadata Parser and Solr Indexer

572-hw2. Home Work 2 Indexing + NER

image-forensics-MFSec17. Automated Large Scale Image Forensics using Tika and Tensorflow

metricx. Python

libtorch-tutorial. Learn libtorch (C++ backend of PyTorch) in an interactive notebook like environment

unmass. Unsupervised NMT based on Masked Seq-to-Seq

202010-pytorch. Pytorch PPT for ISI

007-mt-eval-macro. MT evaluation, use macro-average because rare types are important too.

016-many-eng-v2. Many-English v2

pdf-extractor. A tool to extract text from PDF files with OCR

dialog-data. Dialog Datasets

572-hw3. A web-app for displaying indexed weapons data from Solr

java-plugin-demo. This project demonstrates plugin system which includes an SDK, sample plugins and a plugin app which registers plugins at run time

014-udhr-dataset. Parallel dataset, aligned from United Nations' Universal Declaration of Human Rights (UDHR)

junkdetect. Junk-not-junk, a detector that supports 100 natural languages.

pybind-starter. pybind11 starter code and debug environment

017-pymarian. Pymarian benchmarks

011-imb-learn. Imbalanced Learning

realigner. Re-aligner tool for aligning parallel sentences from comparable documents

tweeter-hackathon. Twitter analysis for hackathon

kannada-osx-keylayout. Kannada keyboard layout setting for OSX