bert-sklearn
NLU-engine-prototype-benchmarks
bert-sklearn | NLU-engine-prototype-benchmarks | |
---|---|---|
1 | 1 | |
293 | 5 | |
- | - | |
0.0 | 2.6 | |
over 1 year ago | about 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
bert-sklearn
-
Quick BERT Pre-Trained Model for Sentiment Analysis with Scikit Wrapper
Sckit-learn wrapper provided by Charles Nainan. GitHub of Scikit Learn BERT wrapper.
NLU-engine-prototype-benchmarks
-
Make your own custom wakeword and other FOSS voice assistant solutions
This will be the next project we focus on. We will benchmark current solutions, improving general data sets, and publish information to help everyone improve upon their current NLU-NLG use cases. All of this is still a heavy work in progress. * NLU engine prototype benchmark and examples * Snips data set converter
What are some alternatives?
bert - TensorFlow code and pre-trained models for BERT
wakeword-data-collector - A prototype CLI in Python where a user can collect all of the recordings needed to produce a wakeword
OpenAI-CLIP - Simple implementation of OpenAI CLIP model in PyTorch.
precise-wakeword-model-maker - Automated, end-to-end wakeword model maker using the Precise Wakeword Engine
kruk - Ukrainian instruction-tuned language models and datasets
secret_sauce_ai - Secret Sauce AI: a coordinated community of tech minded AI enthusiasts
fake-news - Building a fake news detector from initial ideation to model deployment
Leon - 🧠Leon is your open-source personal assistant.
ABSA_Project_4 - This project takes advantange of the parsing and part of speech tagging capabilites of Spacy's pipeline in order to extract aspect/opinion/sentiment triplets. Cluster aspects using unsupervised learning to process sentiment for large amazon review datasets.
indonlu - The first-ever vast natural language processing benchmark for Indonesian Language. We provide multiple downstream tasks, pre-trained IndoBERT models, and a starter code! (AACL-IJCNLP 2020)
tf-transformers - State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.