#8872 语音识别阶段出错[阿里FunASR(内置)] FunASRNano is not registered:Traceback (most recent call last): File

103.151**1 Posted at: 12 hours ago

语音识别阶段出错[阿里FunASR(内置)] 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 84, in run
File "videotrans\task\_stage_recogn.py", line 64, in recogn
File "videotrans\recognition\__init__.py", line 148, 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 291, 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=翻译视频 单视频模式
选择音视频文件: E:/牙刷/视频/逸口乐766/4.mp4,
输出目录: E:/牙刷/视频/逸口乐766/_video_out/4-mp4,
self.cfg.cache_folder='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2'
已选 清理已生成, 未选 CUDA加速
语音识别:阿里FunASR(内置), Fun-ASR-Nano-2512, 发音语言: 简体中文
最长语音持续(秒): 5s
最短语音持续(毫秒): 3000ms
静音分割持续毫秒: 600ms
语音阈值: 0.45
选择VAD: silero
翻译渠道:DeepSeek,发音语言:简体中文,目标语言:越南语
已选 发送完整字幕, AI翻译渠道每批字幕行数:40
配音渠道:Edge-TTS(免费), 配音角色:NamMinh(Male/VN), 目标语言:越南语
Volume:+0%, Speed:+0%, 已选 配音加速, 未选 视频慢速
已选 移除每条字幕配音开头结尾静音缓冲
静音移除力度: default
嵌入软字幕
video duration:25820ms
video information:{'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'hevc', 'audio_codec_name': 'aac', 'width': 576, 'height': 1024, 'time': 25820, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='0d4c145ec2', name='E:/牙刷/视频/逸口乐766/4.mp4', dirname='E:/牙刷/视频/逸口乐766', noextname='4', basename='4.mp4', ext='mp4', target_dir='E:/牙刷/视频/逸口乐766/_video_out/4-mp4', cache_folder='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2', is_cuda=False, source_language='简体中文', source_language_code='zh-cn', source_sub='E:/牙刷/视频/逸口乐766/_video_out/4-mp4/zh-cn.srt', source_wav='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2/zh-cn.wav', source_wav_output='E:/牙刷/视频/逸口乐766/_video_out/4-mp4/zh-cn.m4a', target_language='越南语', target_language_code='vi', target_sub='E:/牙刷/视频/逸口乐766/_video_out/4-mp4/vi.srt', target_wav='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2/target.wav', target_wav_output='E:/牙刷/视频/逸口乐766/_video_out/4-mp4/vi.m4a', translate_type=5, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='NamMinh(Male/VN)', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='zh', recogn_type=3, model_name='Fun-ASR-Nano-2512', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=False, fix_punc=0, app_mode='biaozhun', subtitle_language=None, targetdir_mp4='E:/牙刷/视频/逸口乐766/_video_out/4-mp4/4.mp4', novoice_mp4='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2/novoice.mp4', is_separate=False, embed_bgm=True, instrument='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2/instrument.wav', vocal='D:/软件/win-pyvideotrans-v4.18/tmp/23668/0d4c145ec2/vocal.wav', clear_cache=True, background_music='', subtitle_type=2, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8, batch=False)
video_duration_ms=25820


=
system:Windows-10-10.0.19045-SP0
version:v4.18
frozen:True
language:zh_CN
root_dir:D:/软件/win-pyvideotrans-v4.18

1 Replies

#1 DeepSeek reply at 12 hours ago

根本原因是:当前 v4.18 内置的 funasr 库版本较早,其自动模型注册表中不含 FunASR-Nano 这一模型类,因此调用 AutoModel(model="Fun-ASR-Nano-2512") 时断言失败,与视频文件、显存、CUDA 均无关(你的日志也显示未启用 CUDA)。

解决方案(按优先级)

1. 直接更换识别模型或渠道(最快)

  • 仍在 阿里FunASR(内置) 渠道下,将 识别模型 改为 paraformer-zh 或 sensevoice-small,二者为 funasr 稳定支持模型。
  • 或将 语音识别 渠道改为 Qwen-ASR(内置) + 1.7B 模型(中文推荐,见最佳配置推荐)。

2. 升级到支持该模型的版本
下载官网当前最新的完整包或补丁包覆盖现有目录(覆盖时保留 videotrans/params.json、cfg.json 等配置文件即可)。若仅覆盖 sp.exe 而未覆盖 _internal 文件夹,依赖库不会更新,问题依旧。

3. 源码部署环境自行升级依赖
在项目目录执行 uv add funasr --upgrade(或 uv sync 后手动升级 funasr 与 modelscope),使模型注册表包含 FunASR-Nano。

注意

  • 该报错属于「模型名已列出但底层库不支持」的版本不匹配问题,不要反复重试同一渠道同一模型,也不会因清理缓存而恢复。
  • 若更换模型后仍出现同类 xxx is not registered 报错,说明依赖库与模型列表整体不同步,需执行上面第 2/3 步。

请查阅相关文档:

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