updated comments

app.py

@@ -23,7 +23,7 @@ embedding_model = PretrainedSpeakerEmbedding(
     device=torch.device("cuda" if torch.cuda.is_available() else "cpu"),
 )
 
-
+#Transcribe a bulk of audio files
 def bulk_transcribe(files, model):
     chosen_model = whisper.load_model(model)
     output = ""
@@ -42,13 +42,13 @@ def bulk_transcribe(files, model):
 
     return "Transcripción.txt", output
 
-
+#Getting the file name from the path
 def get_file_name(file):
     file_path = file.split("/")
     file_name = file_path[-1]
     return file_name
 
-
+#The main function that transcribe each audio file
 def transcribe(audio, model):
     num_speakers = 3
     path, error = convert_to_wav(audio)
@@ -103,7 +103,7 @@ audio = Audio()
 
 def segment_embedding(path, segment, duration):
     start = segment["start"]
-    # Whisper overshoots the end timestamp in the last segment
+    
     end = min(duration, segment["end"])
     clip = Segment(start, end)
     waveform, sample_rate = audio.crop(path, clip)