https://github.com/argilla-io/biome-text

Custom Natural Language Processing with big and small models 🌲🌱
https://github.com/argilla-io/biome-text

allennlp data-science natural-language-processing nlp pytorch

Last synced: 4 months ago
JSON representation

Custom Natural Language Processing with big and small models 🌲🌱

• Host: GitHub
• URL: https://github.com/argilla-io/biome-text
• Owner: argilla-io
• License: other
• Archived: true
• Created: 2019-03-05T09:52:16.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-09-08T10:14:06.000Z (over 3 years ago)
• Last Synced: 2024-09-27T16:03:58.293Z (4 months ago)
• Topics: allennlp, data-science, natural-language-processing, nlp, pytorch
• Language: Python
• Homepage: https://recognai.github.io/biome-text/
• Size: 78.7 MB
• Stars: 68
• Watchers: 7
• Forks: 7
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.rst
  • License: LICENSE.txt

Awesome Lists containing this project

README

        


    


    

    






    

        

    

    

        

    

    

        

    

    

        

    

    

        

    





Natural Language Processing library built with AllenNLP

## Quick Links

- [Documentation](https://recognai.github.io/biome-text/)

## Features

* State-of-the-art and not so state-of-the-art models trained with **your own data** with simple workflows.

* **Efficient data reading** for (large) datasets in multiple formats and sources (CSV, Parquet, JSON, etc.).

* **Modular configuration and extensibility** of models, datasets and training runs programmatically or via config files.

* Use via **`cli`** or as plain Python (e.g., inside a Jupyter Notebook)

* **Compatible with AllenNLP**

## Installation

For the installation we recommend setting up a fresh [conda](https://docs.conda.io/en/latest/miniconda.html) environment:

```shell script

conda create -n biome python~=3.7.0 pip>=20.3.0

conda activate biome

```

Once the conda environment is activated, you can install the latest release via pip:

````shell script

pip install -U biome-text

````

After installing *biome.text*, the best way to test your installation is by running the *biome.text* cli command:

```shell script

biome --help

```

## Get started

The best way to see how *biome.text* works is to go through our [first tutorial](https://recognai.github.io/biome-text/master/documentation/tutorials/1-Training_a_text_classifier.html).

Please refer to our [documentation](https://recognai.github.io/biome-text) for more tutorials, detailed user guides and how you can [contribute](https://recognai.github.io/biome-text/master/documentation/community/1-contributing.html) to *biome.text*.

## Licensing

The code in this project is licensed under Apache 2 license.