ivlcic/sour-sarma-pline

This is a Huggingface's transformer library pipeline-frendly model ivlcic/sour-sarma

Usage:

ner = pipeline(
    task="token-classification",
    model="ivlcic/sour-sarma-pline",
    tokenizer="ivlcic/sour-sarma-pline",
    aggregation_strategy="simple",
)
text = " Janez Novak... Metka Kralj,,. in Boris A. Novak živijo v Ljubljani in delajo za Microsoft."
tokens = re.findall(r"\s+|\w+|[^\w\s]", text, flags=re.UNICODE)
result = ner(tokens, is_split_into_words=True, delimiter="")

for r in result[0]:
    print(f'[{text[r['start']:r['end']]}]({r["entity_group"]}@{"%.2f"%r["score"]}|{r["start"]}:{r["end"]})')

Should output something like:

[Janez Novak](PER@1.00|1:12)
[Metka Kralj](PER@1.00|16:27)
[Boris A. Novak](PER@1.00|34:48)
[Ljubljani](LOC@1.00|58:67)
[Microsoft](ORG@1.00|81:90)