#3269 TaskCfg(cache_folder='E:/DUB/tmp/1988/c82a003462', target_dir='E:/New folder/_video_out/2-mp4', remove_noise=False, is_s

176.29* Posted at: 21 hours ago 👁14

Dubbing Error [Edge-TTS(Free)] invalid literal for int() with base 10: ',000'
Traceback (most recent call last):
File "videotrans\task\job.py", line 214, in run
File "videotrans\task\trans_create.py", line 677, in dubbing
File "videotrans\task\trans_create.py", line 953, in _tts
File "videotrans\tts\__init__.py", line 321, in run
File "", line 15, in init
File "videotrans\tts\_edgetts.py", line 29, in post_init
File "videotrans\tts\_base.py", line 74, in post_init
File "videotrans\tts\_base.py", line 87, in _cleantts
File "videotrans\util\en_tn.py", line 265, in call
File "videotrans\util\en_tn.py", line 235, in normalize_numbers
File "re.py", line 209, in sub
File "videotrans\util\en_tn.py", line 159, in _expand_dollars
ValueError: invalid literal for int() with base 10: ',000'


=
system:Windows-10-10.0.19045-SP0
version:v3.97
frozen:True
language:en
root_dir:E:/DUB

1 Replies

The error is caused by the Edge-TTS text normalization process failing to handle a number formatted with a comma as a thousands separator (e.g., "1,000").

This occurs during the text cleaning step before sending text to the Edge-TTS service. The internal normalize_numbers function expects numbers without commas for conversion.

Solution:

  1. Immediate Workaround: In the software's "Advanced Settings" (or "Advanced Options"), locate the "Text Cleaning Rules" or similar section related to TTS preprocessing. Try disabling any option related to "Normalize numbers" or "Text normalization" for the Edge-TTS channel.
  2. Alternative Solution: If the above setting is not available, you can try using a different TTS channel temporarily, such as a local TTS model (if configured), to bypass this specific text processing issue with Edge-TTS.
  3. Check for Updates: Ensure you are using the latest version of the software (v3.97 is current). If a newer version is released, it may contain a fix for this text normalization bug.

If the issue persists:
Please provide the specific line of text from your subtitle file (the en.srt file mentioned in the log) that contains the number format causing the error (e.g., a line with "1,000" or similar). This will help in identifying the exact pattern.

Please refer to the relevant documentation:

Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Related resource