dbmdz/berts

DBMDZ BERT, DistilBERT, ELECTRA, GPT-2 and ConvBERT models

38
/ 100
Emerging

This project offers specialized language models for tasks like text analysis and natural language understanding across various languages including German, Italian, Turkish, French, Dutch, and Ukrainian. It takes raw text in one of these languages and outputs a numerical representation that can be used for tasks like identifying names, places, or sentiment. Researchers, data scientists, and language technology developers can use these models to improve the accuracy of their applications.

159 stars. No commits in the last 6 months.

Use this if you are building an AI application that needs to understand and process text in German, Italian, Turkish, or other supported European languages, especially for historical texts.

Not ideal if your primary language of interest is not covered by the available models or if you require TensorFlow checkpoints.

natural-language-processing historical-text-analysis multilingual-AI text-mining language-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

159

Forks

12

Language

License

MIT

Last pushed

Dec 06, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dbmdz/berts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.