app.py

from transformers import pipeline
import gradio as gr
import os
from huggingface_hub import login


api_key = os.getenv("token")
login(token = api_key)


get_completion = pipeline("ner", model="elnasharomar2/PUNCERT_single_stages_50_epochs")
label_names = ["O","QE","EX","QM","DOT","COM","SEMICOL","COL"]
label_symbol = ["O",'؟!','!','؟','.','،','؛',':']

id2label = {i: label for i, label in zip(label_names,label_symbol)}

def merge_tokens(tokens):
    merged_tokens = []
    for token in tokens:
        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
            # If current token continues the entity of the last one, merge the two tokens
            last_token = merged_tokens[-1]
            last_token['word'] += token['word'].replace('##', '')
            last_token['end'] = token['end']
            last_token['score'] = (last_token['score'] + token['score']) / 2
        else:
            # Otherwise, add the token to the list
            merged_tokens.append(token)

    return merged_tokens

def ner(input):
    output = get_completion(input)
    merged_tokens = merge_tokens(output)
    ## modification
    result =""
    idx = 0
    for i in output:
        result += text[idx:i["start"]]
        result += text[i["start"]:i["end"]] + f"{id2label[i["entity_group"]]}"
        idx = i["end"]
    result+=text[idx:]
    print(result)
    return {"text": result}
    # return {"text": input, "entities": merged_tokens}

gr.close_all()
demo = gr.Interface(fn=ner,
                    inputs=[gr.Textbox(label="Text to find Punctuation", lines=2)],
                    outputs=[gr.HighlightedText(label="Text with Punct")],
                    title="Puncituation Predictor",
                    description="Find Puncituations using the `BERT-base` model under the hood!",
                    allow_flagging="never",
                    examples=[])
demo.launch()