MohammadJRanjbar/persian-sentence-completion

Persian Sentence Completion Classifier

A BERT-based classifier that determines whether a Persian sentence is Complete or Incomplete.
Designed for use in ASR post-processing pipelines (e.g. after speech-to-text).

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

MODEL_ID = "MohammadJRanjbar/persian-sentence-completion"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID)
model.eval()

label_map = {0: "Incomplete", 1: "Complete"}

def classify_sentences(sentences, batch_size=16):
    results = []
    for i in range(0, len(sentences), batch_size):
        batch = sentences[i:i+batch_size]
        inputs = tokenizer(batch, return_tensors="pt", padding=True,
                           truncation=True, max_length=128)
        with torch.no_grad():
            outputs = model(**inputs)
            preds = torch.argmax(outputs.logits, dim=-1)
            results.extend([label_map[p.item()] for p in preds])
    return results

# Example
texts = ["امروز هوا خیلی عالی", "امروز هوا خیلی عالی است."]
print(classify_sentences(texts))
# → ['Incomplete', 'Complete']

Citation

If you use this model, please cite the following works:

@inproceedings{ranjbar-kalahroodi-etal-2026-persianpunc,
    title = "{P}ersian{P}unc: A Large-Scale Dataset and {BERT}-Based Approach for {P}ersian Punctuation Restoration",
    author = "Ranjbar Kalahroodi, Mohammad Javad  and
      Faili, Heshaam  and
      Shakery, Azadeh",
    editor = "Merchant, Rayyan  and
      Megerdoomian, Karine",
    booktitle = "The Proceedings of the First Workshop on {NLP} and {LLM}s for the {I}ranian Language Family",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.silkroadnlp-1.11/",
    doi = "10.18653/v1/2026.silkroadnlp-1.11",
    pages = "105--113",
    ISBN = "979-8-89176-371-5",
}

@misc{kalahroodi2025parsvoicelargescalemultispeakerpersian,
    title = {ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis},
    author = {Mohammad Javad Ranjbar Kalahroodi and Heshaam Faili and Azadeh Shakery},
    year = {2025},
    eprint = {2510.10774},
    archivePrefix = {arXiv},
    primaryClass = {cs.SD},
    url = {https://arxiv.org/abs/2510.10774},
}