app.py

import gradio as gr
from output_beautify import *
import pandas as pd
from load_data import *
import os
from gingerit import *

#os.system("pip install git+https://github.com/openai/whisper.git")
#import whisper

#model = whisper.load_model("small")
#current_size = 'small'


hf_writer = gr.HuggingFaceDatasetSaver('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', "Pavankalyan/chitti_data")
'''
def inference(audio):
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)
    
    mel = whisper.log_mel_spectrogram(audio).to(model.device)
    
    _, probs = model.detect_language(mel)
    
    options = whisper.DecodingOptions(fp16 = False)
    result = whisper.decode(model, mel, options)
    return result.text
    '''
def chitti(query):
    re_table = search(query)
    answers_re_table = [re_table[i][0] for i in range(0,5)]
    answer_links = [re_table[i][3] for i in range(0,5)]
    sorted_indices = sorted(range(len(answers_re_table)), key=lambda k: len(answers_re_table[k]))
    repeated_answers_indices =list()
    for i in range(4):
        if answers_re_table[sorted_indices[i]] in answers_re_table[sorted_indices[i+1]]:
            repeated_answers_indices.append(sorted_indices[i])
    for idx in repeated_answers_indices:
        answers_re_table.pop(idx)
        answer_links.pop(idx)
        
    #return [res1,answers_re_table[0],res2,answers_re_table[1]]
    return [runGinger(answers_re_table[0]),answer_links[0],runGinger(answers_re_table[1]),answer_links[1]]
    #return [re_table[0][0],re_table[0][3],re_table[1][0],re_table[1][3]]

demo = gr.Interface(
    fn=chitti,
    inputs=["text"],
    #inputs=[gr.inputs.Audio(source="microphone", type="filepath", label="Record your audio")],
    outputs=["text","text","text","text"],
    allow_flagging = "manual",
    flagging_options = ["0","1","None"],
    flagging_callback=hf_writer
)
demo.launch()