Update app.py

app.py

@@ -1,34 +1,113 @@
+# 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 os
-import re
-import pywt
-import librosa
-import webrtcvad
-import torchaudio
-import numpy as np
-import gradio as gr
-import scipy.signal
-import soundfile as sf
-from scipy.io.wavfile import write
-from transformers import pipeline
-from transformers import AutoProcessor
-from pyctcdecode import build_ctcdecoder
-from transformers import Wav2Vec2ProcessorWithLM
+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
-# from applyVad import apply_vad
-# from wienerFilter import wiener_filter
-# from highPassFilter import high_pass_filter
-# from waveletDenoise import wavelet_denoise
-from scipy.signal import butter, lfilter, wiener
+from text2int import text_to_int
 
+# Initialize ASR model pipeline
 asr_model = pipeline("automatic-speech-recognition", model="cdactvm/w2v-bert-punjabi")
 
 
@@ -42,6 +121,7 @@ def high_pass_filter(audio, sr, cutoff=300):
 
 # Function to apply wavelet denoising
 def wavelet_denoise(audio, wavelet='db1', level=1):
+    import pywt
     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)))
@@ -51,9 +131,9 @@ def wavelet_denoise(audio, wavelet='db1', level=1):
 # Function to apply a Wiener filter for noise reduction
 def apply_wiener_filter(audio):
     return wiener(audio)
-    
-    
-# # Function to handle speech recognition
+
+
+# Function to handle speech recognition
 def recognize_speech(audio_file):
     audio, sr = librosa.load(audio_file, sr=16000)
     audio = high_pass_filter(audio, sr)
@@ -68,6 +148,7 @@ def recognize_speech(audio_file):
     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
@@ -79,17 +160,17 @@ def sel_lng(lng, mic=None, file=None):
     if lng == "model_1":
         return recognize_speech(audio)
         
-demo=gr.Interface(
+
+# Create a Gradio interface
+demo = gr.Interface(
     fn=sel_lng, 
-      
     inputs=[
-        gr.Dropdown([
-            "model_1"],label="Select Model"),
-        gr.Audio(sources=["microphone","upload"], type="filepath"),
-    ],
-    outputs=[
-        "textbox"
+        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()
+    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"
+)
+
+demo.launch()