#8308 语音识别阶段出错[阿里FunASR(内置)] FunASRNano is not registered:Traceback (most recent call last): File

2408**25f1 Posted at: 2 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\job.py", line 35, in run

File "videotrans\task\job.py", line 101, in process_task

File "videotrans\task\_stage_recogn.py", line 63, in recogn

File "videotrans\recognition\__init__.py", line 141, 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 277, 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=[TransCreate]: uuid='b9c0275ce9', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 转录并翻译字幕
原始输入文件名: H:/纪录片/How.Its.Made.S01-S32.2001-2019.1080p.x264.Collection.Mixed/How.Its.Made.S01.1080p.HDTV.x264.AC3/S01E01 铝箔 滑雪板 隐形眼镜 面包.mkv,
输出结果保存到文件夹: C:/Users/水兵361/Desktop/S01E01 铝箔 滑雪板 隐形眼镜 面包-mkv,
临时文件夹: C:/pyvideotrans/tmp/10452/b9c0275ce9
已选 清理已存在
已启用CUDA加速
未选 降噪
语音识别:阿里FunASR(内置), Fun-ASR-Nano-2512, 发音语言: 英语,
翻译渠道:微软(免费),原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
输出字幕格式: 单字幕, precent=4, hasend=False, should_recogn=True, should_trans=True, should_dubbing=False, should_hebing=False, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=False


=
system:Windows-10-10.0.19045-SP0
version:v4.16
frozen:True
language:zh_CN
root_dir:C:/pyvideotrans

1 Replies

#1 DeepSeek reply at 2 hours ago

这是因为当前软件内打包的 funasr 依赖库版本较旧或组件不完整,不包含 Fun-ASR-Nano 这一类模型的注册类,所以调用时 auto_model 找不到对应类,直接抛出 is not registered。这与已知的 paraformer-zh is not registered 属于同一类依赖/版本问题,与视频本身、CUDA 无关。

解决方案(任选其一)

方案 A:换一个可用的识别模型(最快,推荐)

  1. 你是英文纪录片(How It's Made),直接用 faster-whisper(内置) + large-v3 或 large-v3-turbo 效果最好,无需 Fun-ASR。
  2. 或在 阿里FunASR(内置) 渠道内,把模型从 Fun-ASR-Nano-2512 切换为 paraformer-zh 等经典模型再试。
  3. 重新执行前务必勾选 清理已生成。

方案 B:修复 funasr 依赖

  1. 源码部署(Mac/Linux/Windows 源码):

    uv add -U funasr

    或 uv pip install -U funasr,升级后重启软件再选 Fun-ASR-Nano。

  2. Windows 预打包版(你的情况 frozen:True,v4.16):

    • 重新下载 v4.16 完整包(约 2.7GB) 覆盖,注意 sp.exe、_internal、videotrans 三个都要覆盖,不能只覆盖 sp.exe。
    • 若覆盖后仍报同样错误,删除旧目录 _internal 下所有 __pycache__ 文件夹后再覆盖。
    • 若仍不可用,说明该版本打包的 funasr 尚不支持 Fun-ASR-Nano,只能按方案 A 换模型。

方案 C:确认模型是否下载完整
Fun-ASR-Nano-2512 模型若下载不完整,也可能引发加载异常,可删除 软件目录/models/ 下对应 Fun-ASR-Nano 目录后重新下载。

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