Update app.py

app.py

@@ -1,113 +1,20 @@
-# import warnings
-# warnings.filterwarnings("ignore")
-
-# import os         # for handling of directories.
-# import re         # regular expression.
-# import pywt       # pywavelet for wavelet transformation. used in denoising.
-# import librosa    # used for audio processing.
-# import webrtcvad
-# import torchaudio       # python library for audio processing.
-# import numpy as np      # for mathematical calculations
-# import gradio as gr     # for inferencing.
-# import scipy.signal     # used for signal filtering. used in denoising audio signals.
-# import soundfile as sf  # used for reading and processing audio files.
-# from scipy.io.wavfile import write    # used for saving audio files in wav format.
-# from transformers import pipeline     # used for inferencing.
-# from transformers import AutoProcessor     #used for processing of input data.
-# from pyctcdecode import build_ctcdecoder
-# from transformers import Wav2Vec2ProcessorWithLM
-# from scipy.signal import butter, lfilter, wiener
-# 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
-# # from applyVad import apply_vad
-# # from wienerFilter import wiener_filter
-# # from highPassFilter import high_pass_filter
-# # from waveletDenoise import wavelet_denoise
-
-# asr_model = pipeline("automatic-speech-recognition", model="cdactvm/w2v-bert-punjabi")
-
-
-# # Function to apply a high-pass filter
-# def high_pass_filter(audio, sr, cutoff=300):
-#     nyquist = 0.5 * sr
-#     normal_cutoff = cutoff / nyquist
-#     b, a = butter(1, normal_cutoff, btype='high', analog=False)
-#     filtered_audio = lfilter(b, a, audio)
-#     return filtered_audio
-
-# # Function to apply wavelet denoising
-# def wavelet_denoise(audio, wavelet='db1', level=1):
-#     coeffs = pywt.wavedec(audio, wavelet, mode='per')
-#     sigma = np.median(np.abs(coeffs[-level])) / 0.5
-#     uthresh = sigma * np.sqrt(2 * np.log(len(audio)))
-#     coeffs[1:] = [pywt.threshold(i, value=uthresh, mode='soft') for i in coeffs[1:]]
-#     return pywt.waverec(coeffs, wavelet, mode='per')
-
-# # Function to apply a Wiener filter for noise reduction
-# def apply_wiener_filter(audio):
-#     return wiener(audio)
-    
-    
-# # # Function to handle speech recognition
-# def recognize_speech(audio_file):
-#     audio, sr = librosa.load(audio_file, sr=16000)
-#     audio = high_pass_filter(audio, sr)
-#     audio = apply_wiener_filter(audio)
-#     denoised_audio = wavelet_denoise(audio)
-#     result = asr_model(denoised_audio)
-#     text_value = result['text']
-#     cleaned_text = text_value.replace("[PAD]", "")
-#     converted_to_list = convert_to_list(cleaned_text, text_to_list())
-#     processed_doubles = process_doubles(converted_to_list)
-#     replaced_words = replace_words(processed_doubles)
-#     converted_text = text_to_int(replaced_words)
-#     return converted_text
-
-# def sel_lng(lng, mic=None, file=None):
-#     if mic is not None:
-#         audio = mic
-#     elif file is not None:
-#         audio = file
-#     else:
-#         return "You must either provide a mic recording or a file"
-    
-#     if lng == "model_1":
-#         return recognize_speech(audio)
-        
-# demo=gr.Interface(
-#     fn=sel_lng, 
-      
-#     inputs=[
-#         gr.Dropdown([
-#             "model_1"],label="Select Model"),
-#         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()
-
 
 import warnings
 warnings.filterwarnings("ignore")
 
-import librosa    # used for audio processing.
-import numpy as np      # for mathematical calculations
-import gradio as gr     # for inferencing.
-from transformers import pipeline     # used for inferencing.
-from scipy.signal import butter, lfilter, wiener
-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
+import librosa    # Library for loading and processing audio files.
+import numpy as np      # Library for numerical computations, used for signal processing.
+import gradio as gr     # Library for creating a web-based user interface for inference.
+from transformers import pipeline     # Import pipeline for automatic speech recognition (ASR).
+from scipy.signal import butter, lfilter, wiener  # Signal processing functions for noise reduction.
+
+# Importing custom utility functions for text processing.
+from text2int import text_to_int   # Converts text numbers (e.g., "one") into integers (e.g., 1).
+from isNumber import is_number   # Checks if a string is a number.
+from Text2List import text_to_list   # Converts a text string into a list of words.
+from convert2list import convert_to_list   # Converts processed text into a structured list.
+from processDoubles import process_doubles   # Handles repeated words or numbers in speech recognition output.
+from replaceWords import replace_words   # Replaces specific words in the recognized text with alternatives.
 
 # Initialize ASR model pipeline
 asr_model = pipeline("automatic-speech-recognition", model="cdactvm/w2v-bert-punjabi")