Update: Applied Black formatting

src/transcriber.py

@@ -14,7 +14,12 @@ logger = logging.getLogger(__name__)
 class Transcriber:
     """A class to transcribe audio files using whisperx."""
 
-    def __init__(self, language_code: str = "en", device: str = "cuda", compute_type: str = "float16"):
+    def __init__(
+        self,
+        language_code: str = "en",
+        device: str = "cuda",
+        compute_type: str = "float16",
+    ):
         """
         Init method.
         :param language_code: str: Language code for whisperx transcription (default is "en").
@@ -24,14 +29,17 @@ class Transcriber:
         self.device = device if torch.cuda.is_available() else "cpu"
         # Initialize the transcription and alignment models
         try:
-            self.transcription_model = whisperx.load_model("large-v2", device=self.device, compute_type=compute_type)
-            self.alignment_model, self.metadata = whisperx.load_align_model(language_code=language_code,
-                                                                            device=self.device)
+            self.transcription_model = whisperx.load_model(
+                "large-v2", device=self.device, compute_type=compute_type
+            )
+            self.alignment_model, self.metadata = whisperx.load_align_model(
+                language_code=language_code, device=self.device
+            )
         except Exception as e:
             logger.exception("Failed to initialize models: %s", e)
             raise
         self.transcript_output = None
-        self.hf_token = os.environ.get('HF_TOKEN')
+        self.hf_token = os.environ.get("HF_TOKEN")
 
     def transcribe(self, wav_filename: str, batch_size: int = 16) -> dict:
         """
@@ -48,15 +56,22 @@ class Transcriber:
             result = self.transcription_model.transcribe(audio, batch_size=batch_size)
 
             # Use the alignment model
-            result = whisperx.align(result["segments"], self.alignment_model, self.metadata, audio, self.device,
-                                    return_char_alignments=False)
+            result = whisperx.align(
+                result["segments"],
+                self.alignment_model,
+                self.metadata,
+                audio,
+                self.device,
+                return_char_alignments=False,
+            )
 
             # Clear GPU memory
             self._clear_memory()
 
             # Run Diarization
-            diarize_model = whisperx.DiarizationPipeline(use_auth_token=self.hf_token,
-                                                         device=self.device)
+            diarize_model = whisperx.DiarizationPipeline(
+                use_auth_token=self.hf_token, device=self.device
+            )
             diarize_segments = diarize_model(audio)
             result = whisperx.assign_word_speakers(diarize_segments, result)
 
@@ -76,13 +91,13 @@ class Transcriber:
         """
         try:
             # Save full results to a json file
-            with open(output_json_file, 'w') as f:
+            with open(output_json_file, "w") as f:
                 json.dump(self.transcript_output, f)
 
             # Save just the transcripts to a .txt file
-            transcripts = [seg['text'] for seg in self.transcript_output['segments']]
-            with open(output_txt_file, 'w') as f:
-                f.write('\n'.join(transcripts))
+            transcripts = [seg["text"] for seg in self.transcript_output["segments"]]
+            with open(output_txt_file, "w") as f:
+                f.write("\n".join(transcripts))
         except Exception as e:
             logger.exception("Failed to save transcript: %s", e)
             raise