Add timestamps toggle and update transcription format to include/exclude timestamps

app.py

@@ -127,6 +127,14 @@ class App:
             values=models, font=font_b)
         self.model_combobox.set('medium')  # Set the default value
         self.model_combobox.pack(side=tk.LEFT, fill=tk.X, expand=True)
+        # Timestamps toggle
+        ts_frame = customtkinter.CTkFrame(master)
+        ts_frame.pack(fill=tk.BOTH, padx=10, pady=10)
+        self.timestamps_var = tk.BooleanVar(value=True)
+        self.timestamps_switch = customtkinter.CTkSwitch(
+            ts_frame, text="Include timestamps in transcription",
+            variable=self.timestamps_var, font=font_b)
+        self.timestamps_switch.pack(side=tk.LEFT, padx=5)
         # Progress Bar
         self.progress_bar = ttk.Progressbar(master, length=200, mode='indeterminate')
         # Button actions frame
@@ -184,6 +192,7 @@ class App:
         elif language == self.default_language_text or not language.strip():
             language = None  # This is the same as passing nothing
         verbose = True   # always show transcription progress in the console panel
+        timestamps = self.timestamps_var.get()
         # Show progress bar
         self.progress_bar.pack(fill=tk.X, padx=5, pady=5)
         self.progress_bar.start()
@@ -192,7 +201,7 @@ class App:
         #messagebox.showinfo("Message", "Starting transcription!")
         # Start transcription
         try:
-            output_text = transcribe(path, glob_file, model, language, verbose)
+            output_text = transcribe(path, glob_file, model, language, verbose, timestamps)
         except UnboundLocalError:
             messagebox.showinfo("Files not found error!", 'Nothing found, choose another folder.')
             pass

sample_audio/transcriptions/Armstrong_Small_Step.txt

@@ -1,2 +1,4 @@
 Armstrong_Small_Step
-[0:00:00 --> 0:00:07]: That's one small step for man, one giant leap for mankind.
+────────────────────────────────────────
+
+That's one small step for man, one giant leap for mankind.

sample_audio/transcriptions/Axel_Pettersson_röstinspelning.txt

@@ -1,2 +1,4 @@
 Axel_Pettersson_röstinspelning
-[0:00:00 --> 0:00:15]: Hej, jag heter Axel Pettersson, jag föddes i Örebro 1976. Jag har varit Wikipedia sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.
+────────────────────────────────────────
+
+Hej, jag heter Axel Pettersson, jag föddes i Örebro 1976. Jag har varit Wikipedia sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.

src/_LocalTranscribe.py

@@ -91,7 +91,7 @@ def get_path(path):
     return sorted(media_files)
 
 # Main function
-def transcribe(path, glob_file, model=None, language=None, verbose=False):
+def transcribe(path, glob_file, model=None, language=None, verbose=False, timestamps=True):
     """
     Transcribes audio files in a specified folder using faster-whisper (CTranslate2).
 
@@ -182,10 +182,15 @@ def transcribe(path, glob_file, model=None, language=None, verbose=False):
             segment_list = []
             with open("{}/transcriptions/{}.txt".format(path, title), 'w', encoding='utf-8') as f:
                 f.write(title)
+                f.write('\n' + '─' * 40 + '\n')
                 for seg in segments:
-                    start_ts = str(datetime.timedelta(seconds=seg.start))
-                    end_ts = str(datetime.timedelta(seconds=seg.end))
-                    f.write('\n[{} --> {}]:{}'.format(start_ts, end_ts, seg.text))
+                    text = seg.text.strip()
+                    if timestamps:
+                        start_ts = str(datetime.timedelta(seconds=seg.start))
+                        end_ts = str(datetime.timedelta(seconds=seg.end))
+                        f.write('\n[{} --> {}] {}'.format(start_ts, end_ts, text))
+                    else:
+                        f.write('\n{}'.format(text))
                     f.flush()
                     if verbose:
                         print("   [%.2fs → %.2fs] %s" % (seg.start, seg.end, seg.text))