import warnings
warnings.filterwarnings("ignore")
import os
import re
import gradio as gr
import numpy as np
# import torchaudio
# import nbimporter
from transformers import pipeline
from transformers import AutoProcessor
from pyctcdecode import build_ctcdecoder
from transformers import Wav2Vec2ProcessorWithLM
from text2int import text_to_int
from isNumber import is_number
from Text2List import text_to_list
from convert2list import convert_to_list
from processDoubles import process_doubles
from replaceWords import replace_words

transcriber = pipeline(task="automatic-speech-recognition", model="cdactvm/w2v-bert-2.0-hindi_v1")
processor = AutoProcessor.from_pretrained("cdactvm/w2v-bert-2.0-hindi_v1")

vocab_dict = processor.tokenizer.get_vocab()

sorted_vocab_dict = {k.lower(): v for k, v in sorted(vocab_dict.items(), key=lambda item: item[1])}
decoder = build_ctcdecoder(
    labels=list(sorted_vocab_dict.keys()),
    kenlm_model_path="lm.binary",
    )
processor_with_lm = Wav2Vec2ProcessorWithLM(
    feature_extractor=processor.feature_extractor,
    tokenizer=processor.tokenizer,
    decoder=decoder
    )
processor.feature_extractor._processor_class = "Wav2Vec2ProcessorWithLM"

 
def transcribe(audio):
    # # Process the audio file
    transcript = transcriber(audio)
    text_value = transcript['text']
    print(text_value)
    processd_doubles=process_doubles(text_value)
    converted_to_list=convert_to_list(processd_doubles,text_to_list())
    replaced_words = replace_words(converted_to_list)
    converted_text=text_to_int(replaced_words)
    return converted_text


demo = gr.Interface(
    transcribe,
    gr.Audio(sources="microphone", type="filepath"),
    "text",
)

demo.launch()