QomSSLab/Verdict_Splitter

This repository hosts an XLM-RoBERTa token-classification head trained.

Usage

from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

model_id = "QomSSLab/Verdict_Splitter"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForTokenClassification.from_pretrained(model_id)
tagger = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="simple")

text = "مثال از یک ورودی فارسی"
for entity in tagger(text):
    print(entity)

Labels

• O
• استدلال
• تصمیم
• خارج
• خلع
• مقدمه
• پایانی

Metrics

Validation Metrics

• Precision: 0.7430
• Recall: 0.8457
• F1: 0.7910
• Accuracy: 0.9545

Per-label Breakdown

Label	Precision	Recall	F1	Support
O	0.8468	0.7995	0.8225	394
استدلال	0.9754	0.8776	0.9239	6635
تصمیم	0.9917	0.9608	0.9760	5361
خارج	1.0000	1.0000	1.0000	0
خلع	1.0000	1.0000	1.0000	0
مقدمه	0.9279	0.9982	0.9618	10871
پایانی	0.9728	0.9902	0.9814	1732