File size: 1,510 Bytes
51cfe72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
281308e
51cfe72
 
 
4c728b9
51cfe72
 
 
 
 
 
 
 
 
 
 
d08bc61
 
51cfe72
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
# Import necessary libraries and filter warnings
import warnings
warnings.filterwarnings("ignore")

import os
import re
import torchaudio
import gradio as gr
import numpy as np
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_multiples
from replaceWords import replace_words

pipe = pipeline(task="automatic-speech-recognition", model="cdactvm/English_Model")


def transcribe_english(audio):
    # Process the audio file
    transcript = pipe(audio)
    text_value = transcript['text']
    cleaned_text=text_value.replace("<s>", "")
    converted_to_list=convert_to_list(cleaned_text,text_to_list())
    processd_multiples=process_multiples(converted_to_list)
    replaced_words = replace_words(processd_multiples)
    converted_text=text_to_int(replaced_words)
    return converted_text
    
demo=gr.Interface(
    transcribe_english,
    inputs=[gr.Audio(sources=["microphone","upload"], type="filepath")],
    outputs=["textbox"],
    title="Automatic Speech Recognition",
    description = "Demo for Automatic Speech Recognition. Use microphone to record speech. Please press Record button. Initially it will take some time to load the model. The recognized text will appear in the output textbox",
      ).launch()