Add files via upload

audio_chunker.py

@@ -0,0 +1,14 @@
+import os
+from pydub import AudioSegment
+
+class AudioChunker:
+    @staticmethod
+    def chunk_audio(wav_file_path, output_folder, chunk_length_ms=60000):
+        audio = AudioSegment.from_wav(wav_file_path)
+        chunk_paths = []
+        for i in range(0, len(audio), chunk_length_ms):
+            chunk = audio[i:i + chunk_length_ms]
+            chunk_path = os.path.join(output_folder, f"chunk_{i // chunk_length_ms}.wav")
+            chunk.export(chunk_path, format="wav")
+            chunk_paths.append(chunk_path)
+        return chunk_paths

audio_converter.py

@@ -0,0 +1,7 @@
+from pydub import AudioSegment
+
+class AudioConverter:
+    @staticmethod
+    def convert_mp3_to_wav(mp3_file_path, wav_file_path):
+        audio = AudioSegment.from_mp3(mp3_file_path)
+        audio.export(wav_file_path, format="wav")

audio_recognizer.py

@@ -0,0 +1,20 @@
+import speech_recognition as sr
+
+class AudioRecognizer:
+    def __init__(self, language='en'):
+        self.recognizer = sr.Recognizer()
+        self.language = language
+
+    def recognize_speech(self, audio_file):
+        with sr.AudioFile(audio_file) as source:
+            audio = self.recognizer.record(source)
+            try:
+                text = self.recognizer.recognize_google(audio, language=self.language)
+                print(f"Recognized text from {audio_file}: {text}")  # Debug print
+                return text
+            except sr.UnknownValueError:
+                print(f"Could not understand audio from {audio_file}")
+                return None
+            except sr.RequestError as e:
+                print(f"Could not request results from {audio_file}; {e}")
+                return None

folder_manager.py

@@ -0,0 +1,23 @@
+import os
+import shutil
+
+class FolderManager:
+    @staticmethod
+    def create_output_folder(file_name):
+        new_folder_name = f'output_{file_name}'
+        os.makedirs(new_folder_name, exist_ok=True)
+        return new_folder_name
+
+    @staticmethod
+    def clean_up(folder_path):
+        files_to_keep = ['transcribed_text.txt', 'translated_text.txt', 'translated_speech.mp3']
+        for filename in os.listdir(folder_path):
+            if filename not in files_to_keep:
+                file_path = os.path.join(folder_path, filename)
+                try:
+                    if os.path.isdir(file_path):
+                        shutil.rmtree(file_path)
+                    else:
+                        os.remove(file_path)
+                except Exception as e:
+                    print(f"Error deleting {file_path}: {e}")

main.py

@@ -0,0 +1,39 @@
+import os
+from folder_manager import FolderManager
+from audio_converter import AudioConverter
+from audio_chunker import AudioChunker
+from audio_recognizer import AudioRecognizer
+from translator_module import TextTranslator
+from text_to_speech import TextToSpeech
+from text_saver import TextSaver
+
+def main(mp3_file_path):
+    base_file_name = os.path.splitext(os.path.basename(mp3_file_path))[0]
+    output_folder = FolderManager.create_output_folder(base_file_name)
+
+    wav_file_path = os.path.join(output_folder, 'converted_audio.wav')
+    AudioConverter.convert_mp3_to_wav(mp3_file_path, wav_file_path)
+
+    chunk_paths = AudioChunker.chunk_audio(wav_file_path, output_folder)
+
+    recognizer = AudioRecognizer(language='en')
+    translator = TextTranslator(source_language='en', target_language='te')
+
+    combined_text = ""
+    for chunk_path in chunk_paths:
+        recognized_text = recognizer.recognize_speech(chunk_path)
+        if recognized_text:
+            combined_text += recognized_text + " "
+
+    if combined_text.strip():
+        TextSaver.save_text_files(combined_text, "", output_folder)
+
+        translated_text = translator.translate_text(combined_text)
+        if translated_text:
+            TextSaver.save_text_files("", translated_text, output_folder)
+            TextToSpeech.convert_text_to_speech(translated_text, os.path.join(output_folder, 'translated_speech.mp3'))
+
+    FolderManager.clean_up(output_folder)
+
+if __name__ == "__main__":
+    main('C:/Users/dkodurul_stu/WIP-Projects/sample.mp3')

text_saver.py

@@ -0,0 +1,15 @@
+import os
+
+class TextSaver:
+    @staticmethod
+    def save_text_files(transcribed_text, translated_text, output_folder):
+        transcribed_file_path = os.path.join(output_folder, 'transcribed_text.txt')
+        translated_file_path = os.path.join(output_folder, 'translated_text.txt')
+
+        if transcribed_text.strip():
+            with open(transcribed_file_path, 'w', encoding='utf-8') as f:
+                f.write(transcribed_text)
+
+        if translated_text.strip():
+            with open(translated_file_path, 'w', encoding='utf-8') as f:
+                f.write(translated_text)

text_to_speech.py

@@ -0,0 +1,14 @@
+from gtts import gTTS
+import os
+
+class TextToSpeech:
+    @staticmethod
+    def convert_text_to_speech(text, output_file):
+        try:
+            # Initialize gTTS with the text, language set to Telugu ('te'), and slow set to False
+            tts = gTTS(text=text, lang='te', slow=False)
+            # Save the generated speech to an MP3 file
+            tts.save(output_file)
+            print(f"Audio saved to {output_file}")
+        except Exception as e:
+            print(f"Failed to convert text to speech: {e}")

translator_module.py

@@ -0,0 +1,15 @@
+from googletrans import Translator
+
+class TextTranslator:
+    def __init__(self, source_language='en', target_language='te'):
+        self.translator = Translator()
+        self.source_language = source_language
+        self.target_language = target_language
+
+    def translate_text(self, text):
+        try:
+            translated = self.translator.translate(text, src=self.source_language, dest=self.target_language)
+            return translated.text
+        except Exception as e:
+            print(f"Translation failed: {e}")
+            return None