Formatting

src/engines/TTSEngine/BaseTTSEngine.py

@@ -7,52 +7,53 @@ from abc import ABC, abstractmethod
 
 from ..BaseEngine import BaseEngine
 
+
 class Word(TypedDict):
     start: str
     end: str
     text: str
 
-class BaseTTSEngine(BaseEngine):
 
+class BaseTTSEngine(BaseEngine):
     @abstractmethod
     def synthesize(self, text: str, path: str) -> str:
         pass
 
     def time_with_whisper(self, path: str) -> list[Word]:
-            """
-            Transcribes the audio file at the given path using a pre-trained model and returns a list of words.
+        """
+        Transcribes the audio file at the given path using a pre-trained model and returns a list of words.
 
-            Args:
-                path (str): The path to the audio file.
+        Args:
+            path (str): The path to the audio file.
 
-            Returns:
-                list[Word]: A list of Word objects representing the transcribed words.
-                Example:
-                ```json
-                [
-                    {
-                        "start": "0.00",
-                        "end": "0.50",
-                        "text": "Hello"
-                    },
-                    {
-                        "start": "0.50",
-                        "end": "1.00",
-                        "text": "world"
-                    }
-                ]
-                ```
-            """
-            device = "cuda" if is_available() else "cpu"
-            audio = wt.load_audio(path)
-            model = wt.load_model("tiny", device=device)
+        Returns:
+            list[Word]: A list of Word objects representing the transcribed words.
+            Example:
+            ```json
+            [
+                {
+                    "start": "0.00",
+                    "end": "0.50",
+                    "text": "Hello"
+                },
+                {
+                    "start": "0.50",
+                    "end": "1.00",
+                    "text": "world"
+                }
+            ]
+            ```
+        """
+        device = "cuda" if is_available() else "cpu"
+        audio = wt.load_audio(path)
+        model = wt.load_model("tiny", device=device)
 
-            result = wt.transcribe(model=model, audio=audio)
-            results = [word for chunk in result for word in chunk["words"]]
-            for result in results:
-                # Not needed for the current use case
-                del result["confidence"]
-            return results
+        result = wt.transcribe(model=model, audio=audio)
+        results = [word for chunk in result for word in chunk["words"]]
+        for result in results:
+            # Not needed for the current use case
+            del result["confidence"]
+        return results
 
     def force_duration(self, duration: float, path: str):
         """
@@ -70,8 +71,10 @@ class BaseTTSEngine(BaseEngine):
         if audio_clip.duration > duration:
             speed_factor = audio_clip.duration / duration
 
-            new_audio = audio_clip.fx(mp.vfx.speedx, speed_factor, final_duration=duration)
+            new_audio = audio_clip.fx(
+                mp.vfx.speedx, speed_factor, final_duration=duration
+            )
 
-            new_audio.write_audiofile(path, codec='libmp3lame')
+            new_audio.write_audiofile(path, codec="libmp3lame")
 
         audio_clip.close()