Created project tree

Author: Janosik15041

README.md

@@ -1 +1,7 @@
 # voice_ukr_to_eng
+
+## Setup
+
+
+## Use
+

results/.gitkeep

@@ -0,0 +1,24 @@
+import uuid
+from utils import (
+    get_aduio_from_youtube_video, 
+    transcribe, 
+    translate, 
+    create_voice_samples_dataset,
+    generate_translated_speech,
+    merge_audio_samples
+)
+
+
+def main(url: str):
+    audio = get_aduio_from_youtube_video(audio)
+    transcription = transcribe(audio)               # [(time_start, time_end, text), ...]
+    translation = translate(transcription)          # [(time_start, time_end, translated_text), ...]
+    path_to_voice_samples = create_voice_samples_dataset(audio, transcription)
+    path_to_generated_audio = generate_translated_speech(path_to_voice_samples, translation)
+    path_to_result_audio = merge_audio_samples(path_to_generated_audio, translation)
+    return path_to_result_audio
+
+if __name__ == "__main__":
+    url = "https://www.youtube.com/watch?v=prfaWHQoxVg"
+    main(url)
+    

src/main.py

@@ -0,0 +1,37 @@
+from typing import Dict, List
+
+
+class TranscriptionElement:
+    """Basic element of Transcription with time stamps. 
+    Full transcription is a list of such elements"""
+    time_start: float
+    time_end: float
+    text: str
+
+
+def get_aduio_from_youtube_video(url: str):
+    raise NotImplemented()
+
+
+def transcribe(audio) -> List[TranscriptionElement]:
+    raise NotImplemented()
+
+
+def translate() -> List[TranscriptionElement]:
+    raise NotImplemented()
+
+
+def create_voice_samples_dataset(audio, transcription: List[TranscriptionElement]) -> str:
+    raise NotImplemented()
+
+
+def generate_translated_speech(path_to_voice_samples: str, translation: List[TranscriptionElement]):
+    raise NotImplemented()
+
+
+def merge_audio_samples(path_to_generated_audio: str, transcription: List[TranscriptionElement]):
+    raise NotImplemented()
+    
+
+if __name__ == "__main__":
+    print("Hello")