Emanuel Huber's repositories
porttagger
A Brazilian Portuguese part-of-speech tagger according to Universal Dependencies
twitter-br
Language model training for Tweets in Brazilian Portuguese
twitter-portuguese-tokenizer
A portuguese Twitter Tokenizer for DANTE dataset
br-address-parser
A simple parser for brazilian addresses
UD_Portuguese-Porttinari
Easy access to NILC's Portinari-Base dataset
AdaptiveCards
A new way for developers to exchange card content in a common and consistent way.
Amive-PLN
RepositĂłrio referente ao projeto de identificação de sintomas de depressĂŁo em postagens de mĂdias sociais em portuguĂŞs do Brasil
anomaly-gan-av
Real-time anomaly detection using video data from autonomous vehicle
Conllu-File-Comparator
Programa em Python que compara as relações de dependência "nsubj", "csubj", "obj" e "iobj" entre um arquivo ".conllu" de teste e outro ".conllu" de referência.
dante-parser
Automatic parsing of Brazilian Tweets for the stock market domain
fipe
Tabela Fipe API :car::moneybag: http://deividfortuna.github.io/fipe/v2
ml-studies
Studies of machine learning concepts
mlops-e2e
MLOps End-to-End Example using Amazon SageMaker Pipeline, AWS CodePipeline and AWS CDK
openvoronoi
2D voronoi diagram for point and line-segment sites using incremental topology-oriented algorithm. C++ with python bindings. Licensed under LGPL2.1.
simple-mlops
Simple MLOps example on Wine dataset
single-repo-front-back
my test
stanza-train-br
Model training tutorials for the Stanza Python NLP Library
subword-sequence-tagging
Code for the paper: Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation (ACL 2019)
sw-studies
General software-engineering studies
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
transformers-pytorch
Transformers implementation from scratch with PyTorch
UD_Portuguese-DANTE
Easy access to NILC's DANTE dataset
webdataset
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.