This library was developed with the idea to help us to create punctuation restoration models to memorize trained parameters, data, training visualization, etc. The Library doesn't use any high-level frameworks, such as PyTorch-lightning or Keras, to reduce the level entry threshold. Feel free to fork this repo and edit model or dataset classes for your purposes. Our team always uses the latest version and features of Python. We started with Python 3.9, but realized, that there is no FastAPI image for Python 3.9. There is several PRs in image repositories, but no response from maintainers. So we decided to change code which we use in production to work with the 3.8 version of Python. In some functions we have 3.9 code, but we still use them, these functions are needed only for development purposes.

Features

  • Choose model from releases section
  • Model training from scratch
  • Fine-tuning already trained model
  • Model architecture is pretty easy and straight forward
  • Predict what symbol should go after token
  • Reduce demsions
  • DeepPavlov/rubert-base-cased-sentence language model

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Neuro-comma

Neuro-comma Web Site

You Might Also Like
Free CRM Software With Something for Everyone Icon
Free CRM Software With Something for Everyone

216,000+ customers in over 135 countries grow their businesses with HubSpot

Think CRM software is just about contact management? Think again. HubSpot CRM has free tools for everyone on your team, and it’s 100% free. Here’s how our free CRM solution makes your job easier.
Get free CRM
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Neuro-comma!

Additional Project Details

Programming Language

Python

Related Categories

Python Transformer Models

Registered

2023-04-21