Update Tamil_number_conversion.py

Tamil_number_conversion.py

@@ -1,78 +1,65 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-# In[1]:
-
-
-import gradio as gr
-import librosa
-import numpy as np
-import pywt
-import nbimporter
-from scipy.signal import butter, lfilter, wiener
-from scipy.io.wavfile import write
-from transformers import pipeline
-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
-
-asr_model = pipeline("automatic-speech-recognition", model="cdactvm/w2v-bert-tamil_new")
-
-# 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("<s>", "")
-    print(cleaned_text)
-    converted_to_list = convert_to_list(cleaned_text, text_to_list())
-    print(converted_to_list)
-    processed_doubles = process_doubles(converted_to_list)
-    print(processed_doubles)
-    replaced_words = replace_words(processed_doubles)
-    print(replaced_words)
-    converted_text = text_to_int(replaced_words)
-    print(converted_text)
-    return converted_text
-
-# Gradio Interface
-gr.Interface(
-    fn=recognize_speech,
-    inputs=gr.Audio(sources=["microphone","upload"], type="filepath"),
-    outputs="text",
-    title="Speech Recognition with Advanced Noise Reduction & Hindi ASR",
-    description="Upload an audio file, and the system will use high-pass filtering, Wiener filtering, and wavelet-based denoising, then a Hindi ASR model will transcribe the clean audio."
-).launch()
-
-
-# In[ ]:
-
-
-
-
+import gradio as gr
+import librosa
+import numpy as np
+import pywt
+import nbimporter
+from scipy.signal import butter, lfilter, wiener
+from scipy.io.wavfile import write
+from transformers import pipeline
+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
+
+asr_model = pipeline("automatic-speech-recognition", model="cdactvm/w2v-bert-tamil_new")
+
+# 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("<s>", "")
+    print(cleaned_text)
+    converted_to_list = convert_to_list(cleaned_text, text_to_list())
+    print(converted_to_list)
+    processed_doubles = process_doubles(converted_to_list)
+    print(processed_doubles)
+    replaced_words = replace_words(processed_doubles)
+    print(replaced_words)
+    converted_text = text_to_int(replaced_words)
+    print(converted_text)
+    return converted_text
+
+# Gradio Interface
+gr.Interface(
+    fn=recognize_speech,
+    inputs=gr.Audio(sources=["microphone","upload"], type="filepath"),
+    outputs="text",
+    title="Speech Recognition with Advanced Noise Reduction & Hindi ASR",
+    description="Upload an audio file, and the system will use high-pass filtering, Wiener filtering, and wavelet-based denoising, then a Hindi ASR model will transcribe the clean audio."
+).launch()