kredor / token-classification updated 2 years ago

punctuate-all

Name: punctuate-all
Author: kredor

This is based on Oliver Guhr's work. The difference is that it is a finetuned xlm-roberta-base instead of an xlm-roberta-large and on twelve languages instead of four. The languages are: English, German, French, Spanish, Bulgarian, Italian, Polish, Dutch, Czech, Portugese, Slovak, Slovenian.

Params

—

Context

512

Downloads 30d

708 K

Likes

Commercial use: allowed mit Not gated View on Hugging Face ↗

Download history

daily snapshots · 10 days

709 K692 K

Jul 28Jul 31Aug 3Aug 6

Specifications

Architecture: XLMRobertaForTokenClassification
Context length: 512
Vocabulary: 250,002
Layers / heads: 12 / 12
Licence: mit
First seen on the Hub: 2022-04-09
Training datasets: wmt/europarl
Added to our catalog: 2026-07-28

Compare with

indonesian-roberta-base-posp-tagger 3.1 M stanford-deidentifier-base 1.9 M bert-base-NER 1.3 M bert-large-cased-finetuned-conll03-english 699 K sat-3l-sm 558 K ner-english-fast 543 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB