#7745 ASR Error [FunASR(Local)] Traceback (most recent call last): File

202.150**5 Posted at: 1 hour ago

ASR Error [FunASR(Local)] Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 489, in paraformer
KeyError: 'sentence_info'

Traceback (most recent call last):
File "videotrans\task\job.py", line 106, in run
File "videotrans\task\_speech2text.py", line 153, in recogn
File "videotrans\recognition\__init__.py", line 243, in run
File "videotrans\recognition\_base.py", line 142, in run
File "videotrans\recognition\_funasr.py", line 68, in _exec
File "videotrans\configure\_base.py", line 290, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 489, in paraformer
KeyError: 'sentence_info'
TaskCfgSTT(is_cuda=True, uuid='31684828af', cache_folder='E:/ytrans/tmp/24056/31684828af', target_dir='E:/ytrans/output/recogn', source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='E:/ytrans/output/recogn/25-2.srt', target_wav=None, target_wav_output=None, name='E:/PH/Nana/A/audio/25-2.m4a', noextname='25-2', basename='25-2.m4a', ext='m4a', dirname='E:/PH/Nana/A/audio', shound_del_name=None, detect_language='zh-cn', recogn_type=3, model_name='paraformer-zh', shibie_audio='E:/ytrans/tmp/24056/31684828af/25-2-1790830886.0961182.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.97
frozen:True
language:en
root_dir:E:/ytrans

#1 DeepSeek reply at 1 hour ago

This error means the FunASR (paraformer-zh) engine returned a result dict that does not contain the key sentence_info, so the recognition step failed inside stt_fun.py.

Possible causes:

The paraformer-zh model files are incomplete or corrupted (very common, since FunASR models are downloaded on first use and downloads frequently fail).

A partially downloaded model can still load but return an unexpected structure.
Your version is old.

You stated v3.97, while the current version is v4.14.

This error and the surrounding FunASR handling have been changed/optimized in later releases.

Troubleshooting steps:

Upgrade to the latest version (full package recommended), then overwrite the patch package: https://pyvideotrans.com/downpackage
If it still fails, delete the corrupted FunASR model folder and let it re-download.

FunASR models are stored under the software models/ directory; remove the incomplete paraformer-zh related folder, then run again so it re-downloads.
- If the download always fails, manually download the model.
  
  See: https://pyvideotrans.com/aboutmodels
As a workaround, use a different ASR channel (e.g.

faster-whisper(内置) with large-v3) and confirm whether recognition works.

This helps isolate whether the problem is specific to FunASR.
Ensure the software path is a simple English/digit path (you have E:/ytrans, which is fine), and that your filenames have no unusual characters.

If none of the above helps, provide the latest log file (about the last 30 lines) from the logs/ folder under your install directory.

#7745 ASR Error [FunASR(Local)] Traceback (most recent call last): File

1 Replies

请查阅相关文档：

Post Your Reply

Related resource