#8885 Error during speech recognition stage[Alibaba FunASR(Built-in)] FunASRNano is not registered:Traceback (most recent call

36.37**7 Posted at: 3 hours ago

Error during speech recognition stage[Alibaba FunASR(Built-in)] FunASRNano is not registered:Traceback (most recent call last):
File "videotrans\process\stt_funasr.py", line 51, in funasr_mlt
File "funasr\auto\auto_model.py", line 135, in init

model, kwargs = self.build_model(**kwargs)

File "funasr\auto\auto_model.py", line 281, in build_model

assert model_class is not None, f'{kwargs["model"]} is not registered'

AssertionError: FunASRNano is not registered

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 85, in run
File "videotrans\task\_stage_recogn.py", line 64, in recogn
File "videotrans\recognition\__init__.py", line 178, in run
File "videotrans\recognition\_base.py", line 101, in run
File "videotrans\recognition\_funasr.py", line 70, in _exec
File "videotrans\configure\base.py", line 300, in _new_process
videotrans.configure.excepts.VideoTransError: FunASRNano is not registered:Traceback (most recent call last):
File "videotrans\process\stt_funasr.py", line 51, in funasr_mlt
File "funasr\auto\auto_model.py", line 135, in init

model, kwargs = self.build_model(**kwargs)

File "funasr\auto\auto_model.py", line 281, in build_model

assert model_class is not None, f'{kwargs["model"]} is not registered'

AssertionError: FunASRNano is not registered

trk=Translation V/A 单视频模式
Select Media File: D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/ឆ្លងភពរកប៉ា_001.mp4,
Output Directory: D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4,
self.cfg.cache_folder='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea'
Not-Selected Clear Output, Selected Enable accelerator
Selected Denoise,Denoise Model:dpdfnet2.onnx
STT Service:Alibaba FunASR(Built-in), Fun-ASR-Nano-2512, Spoken: Simplified Chinese
Max Speech Duration (s): 5s
Min Speech Duration (ms): 3000ms
Min Silence Duration for Split (ms): 600ms
VAD Speech Threshold: 0.45
VAD Engine: silero
TranslateSrt:Gemini AI,Spoken:Simplified Chinese,Target:Khmer
Selected SendSRT, AI Translation Batch Size (Lines):40
TTS Service:Edge-TTS (Free), Voices:Piseth(Male/KH), Target:Khmer
Volume:+0%, Speed:+0%, Selected TTS Speedup, Not-Selected Slow Video
Selected Trim Start/End Silence in Dubbed Segments
Silence Removal Intensity: default
No Subtitles
Selected Separate Vocal/BGM, Model:spleeter,Selected Re-embed BGM, Background Audio Volume Multiplier:0.8, Loop BGMD:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/vocal.wavD:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/instrument.wav
video duration:901666ms
video information:{'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 718, 'height': 1280, 'time': 901666, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='bd698bccea', name='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/ឆ្លងភពរកប៉ា_001.mp4', dirname='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា', noextname='ឆ្លងភពរកប៉ា_001', basename='ឆ្លងភពរកប៉ា_001.mp4', ext='mp4', target_dir='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4', cache_folder='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea', is_cuda=True, source_language='Simplified Chinese', source_language_code='zh-cn', source_sub='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4/zh-cn.srt', source_wav='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/zh-cn.wav', source_wav_output='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4/zh-cn.m4a', target_language='Khmer', target_language_code='km', target_sub='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4/km.srt', target_wav='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/target.wav', target_wav_output='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4/km.m4a', translate_type=6, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Piseth(Male/KH)', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, tts_model_name=None, detect_language='zh', recogn_type=3, model_name='Fun-ASR-Nano-2512', shibie_audio=None, remove_noise=True, enable_diariz=False, nums_diariz=0, rephrase=False, fix_punc=0, app_mode='biaozhun', subtitle_language=None, targetdir_mp4='D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/_video_out/ឆ្លងភពរកប៉ា_001-mp4/ឆ្លងភពរកប៉ា_001.mp4', novoice_mp4='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/novoice.mp4', is_separate=True, embed_bgm=True, instrument='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/instrument.wav', vocal='D:/Hak/win-pyvideotrans-v4.19/tmp/29612/bd698bccea/vocal.wav', clear_cache=False, background_music='', subtitle_type=0, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8, batch=False)
video_duration_ms=901666


=
system:Windows-10-10.0.26300-SP0
version:v4.19
frozen:True
language:en_US
root_dir:D:/Hak/win-pyvideotrans-v4.19

1 Replies

#1 DeepSeek reply at 3 hours ago

This is because the bundled funasr library version is too old and does not contain the model class FunASRNano, so build_model fails at the registration check. This is a problem with the library version, not with your settings or the model file.

Solutions (in order of preference):

  1. Switch to a model supported by the current version: In the Alibaba FunASR(Built-in) channel, change Model from Fun-ASR-Nano-2512 to paraformer-zh (or sensevoice-small), then run again. In practice, Chinese recognition works well with these models.
  2. Or switch to another speech recognition channel: Select Qwen-ASR(Built-in) + 1.7B (recommended for Chinese) from STT Service, or select Firered Chinese(Built-in).
  3. If you are using the packaged Windows version (the log shows frozen:True, v4.19): Download the latest v4.19 patch package from https://pyvideotrans.com/downpackage, overwrite it, and try again. Do not selectively overwrite only sp.exe; you must copy over the _internal and videotrans folders as well.
  4. If you deployed from source: Run uv add -U funasr (or pip install -U funasr) to upgrade the funasr dependency, then restart the software.

Reminder: The path D:/Hak/to_translate/New folder/ឆ្លងភពរកប៉ា/... contains spaces and Khmer characters. It is recommended to change it to a short path consisting only of English letters and digits (for example D:/hak/video1.mp4) before processing. Otherwise, other FFmpeg-related errors are likely in later stages.

Please refer to the related documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
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.

Dondate via ko-fi.com

Related resource