liuyang commited on
Commit
aa984fe
·
1 Parent(s): caef0e2

enable result printing and comment out text cleanup regex

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -432,7 +432,7 @@ class WhisperTranscriber:
432
 
433
  transcription_time = time.time() - start_time
434
  print(f"Full audio transcribed in {transcription_time:.2f} seconds using batch size {batch_size}")
435
- #print(results)
436
  return results, detected_language
437
 
438
  # Removed audio cutting; transcription is done once on the full (preprocessed) audio
@@ -642,7 +642,7 @@ class WhisperTranscriber:
642
  # Clean up text
643
  for segment in grouped_segments:
644
  segment["text"] = re.sub(r"\s+", " ", segment["text"]).strip()
645
- segment["text"] = re.sub(r"\s+([.,!?])", r"\1", segment["text"])
646
 
647
  return grouped_segments
648
 
 
432
 
433
  transcription_time = time.time() - start_time
434
  print(f"Full audio transcribed in {transcription_time:.2f} seconds using batch size {batch_size}")
435
+ print(results)
436
  return results, detected_language
437
 
438
  # Removed audio cutting; transcription is done once on the full (preprocessed) audio
 
642
  # Clean up text
643
  for segment in grouped_segments:
644
  segment["text"] = re.sub(r"\s+", " ", segment["text"]).strip()
645
+ #segment["text"] = re.sub(r"\s+([.,!?])", r"\1", segment["text"])
646
 
647
  return grouped_segments
648