A PyTorch implementation of ScanSSD Scanning Single Shot MultiBox Detector by Parag Mali. It was developed using SSD implementation by Max deGroot.
(Unofficial) Pytorch implementation of JointBERT: BERT for Joint Intent Classification and Slot Filling.
"Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models."
Summarization, translation, Q&A, text generation and more at blazing speed using a T5 version implemented in ONNX.
Carrot2 is a programming library for clustering text. It can automatically discover groups of related documents and label them with short key terms or phrases.
python freamework to extract features from speech.
Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow
A pre-trained language model for English Tweets.
OpenUE is an open-source toolkit that provides a off-the-shelf framework to implement lots of NLP extraction tasks.
Open source audio annotation tool for humans
Texthero is very simple to learn and designed to be used on top of Pandas.
Simple application using sentece embedding to project the documents in a high dimensional space and find most similarities using cosine similarity.
Simple application using transformers models to predict next word or a masked word in a sentence.
Compares embedding vectors for two different texts visually and by numerical metrics.
make transformers serving fast by adding a turbo to your inference engine!
Question Answering using Albert and Electra.
The Stanford NLP Group's official Python NLP library.
Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community.
An exhaustive paper list for Text Summarization, covering papers from eight top conferences
Pre-trained PhoBERT models are the state-of-the-art language models for Vietnamese
TextBrewer is a PyTorch-based toolkit for distillation of NLP models.
An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.
Forte is a toolkit for building Natural Language Processing pipelines, featuring cross-task interaction, adaptable data-model interfaces and many more.
A small example of an interactive visualization for attention values as being used by transformer language models like GPT2 and BERT.
Fine-tuned pre-trained GPT2 for custom topic specific text generation. Such system can be used for Text Augmentation.