From b6e6e80cfbeb626c13a3f787952e18eb048d71bc Mon Sep 17 00:00:00 2001
From: Heiko Joerg Schick <info@schihei.de>
Date: Thu, 22 May 2025 20:31:18 +0200
Subject: [PATCH] Added progress bar

---
 src/transcriber.py | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/src/transcriber.py b/src/transcriber.py
index c493cfd..9dc158f 100644
--- a/src/transcriber.py
+++ b/src/transcriber.py
@@ -1,6 +1,7 @@
 # Audio transcription logic using Faster Whisper
 
 from faster_whisper import WhisperModel
+from tqdm import tqdm
 
 def transcribe_audio(input_path, output_path, model_size="medium", turbo=False):
     """
@@ -35,10 +36,31 @@ def transcribe_audio(input_path, output_path, model_size="medium", turbo=False):
     if model is None:
         raise RuntimeError("Failed to initialize Whisper model with any compute type")
 
-    segments, info = model.transcribe(input_path)
+    # Create a progress bar for the transcription process
+    print(f"Starting transcription of {input_path}...")
+    
+    # Initialize a progress bar without a known total
+    # We'll update it as segments come in
+    progress_bar = tqdm(desc="Transcribing", unit="segment")
+    
+    # Transcribe the audio
+    segments_generator, info = model.transcribe(input_path)
+    
+    # Process the segments and update the progress bar as we go
     transcription = ""
-    for segment in segments:
+    segment_count = 0
+    
+    for segment in segments_generator:
         transcription += segment.text.strip() + "\n"
+        segment_count += 1
+        progress_bar.update(1)
+        
+    # Close the progress bar
+    progress_bar.close()
+    
+    print(f"Transcription complete. Processed {segment_count} segments.")
+    
     with open(output_path, "w", encoding="utf-8") as f:
         f.write(transcription.strip())
+    
     return transcription.strip()