app.py

import gradio as gr
import hazm
import typing

normalizer = hazm.Normalizer()
sent_tokenizer = hazm.SentenceTokenizer()
word_tokenizer = hazm.WordTokenizer()

tagger = hazm.POSTagger(
            model=str("pos_tagger.model")
        )

def preprocess_text(text: str) -> typing.List[typing.List[str]]:
        """Split/normalize text into sentences/words with hazm"""
        text = normalizer.normalize(text)
        processed_sentences = []

        for sentence in sent_tokenizer.tokenize(text):
            words = word_tokenizer.tokenize(sentence)
            processed_words = fix_words(words)
            processed_sentences.append(" ".join(processed_words))

        return  processed_sentences.decode('utf-8')
    
def fix_words(words: typing.List[str]) -> typing.List[str]:
        fixed_words = []

        for word, pos in tagger.tag(words):
            if pos[-1] == "Z":
                if word[-1] != "ِ":
                    if (word[-1] == "ه") and (word[-2] != "ا"):
                        word += "‌ی"
                word += "ِ"
                    

            fixed_words.append(word)

        return fixed_words
        #return tagger.tag(words)
    
iface = gr.Interface(fn=preprocess_text, inputs="text", outputs="text")
iface.launch()