#4607 语音识别阶段出错 [Qwen-ASR(本地)] Could not read model from D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa/data/nagisa_v001

13.250* Posted at: 1 day ago 👁22

语音识别阶段出错 [Qwen-ASR(本地)] Could not read model from D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa/data/nagisa_v001.model
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "multiprocessing\pool.py", line 125, in worker
File "videotrans\process\stt_fun.py", line 817, in qwen3asr_fun
File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal\qwen_asr\__init__.py", line 20, in

from .inference.qwen3_asr import Qwen3ASRModel

File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal\qwen_asr\inference\qwen3_asr.py", line 32, in

from .qwen3_forced_aligner import Qwen3ForcedAligner

File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal\qwen_asr\inference\qwen3_forced_aligner.py", line 21, in

import nagisa

File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa\__init__.py", line 8, in

tagger  = Tagger()

File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa\tagger.py", line 38, in init

self._model = model.Model(self._hp, params)

File "D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa\model.py", line 75, in init

model.populate(params)

File "_dynet.pyx", line 1461, in _dynet.ParameterCollection.populate
File "_dynet.pyx", line 1516, in _dynet.ParameterCollection.populate_from_textfile
RuntimeError: Could not read model from D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa/data/nagisa_v001.model
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\_speech2text.py", line 159, in recogn
File "videotrans\recognition\__init__.py", line 259, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_qwenasrlocal.py", line 48, in _exec
File "videotrans\configure\_base.py", line 285, in _new_process
File "videotrans\process\signelobj.py", line 13, in result
File "multiprocessing\pool.py", line 774, in get
RuntimeError: Could not read model from D:\整個硬盤臨時存放\win-videotrans-v3.66-tiny\_internal agisa/data/nagisa_v001.model
TaskCfgSTT(is_cuda=True, uuid='e167d65ac9', cache_folder='D:/整個硬盤臨時存放/win-videotrans-v3.66-tiny/tmp/37064/e167d65ac9', target_dir='D:/整個硬盤臨時存放/win-videotrans-v3.66-tiny/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='D:/整個硬盤臨時存放/win-videotrans-v3.66-tiny/output/recogn/首台风机基础浇筑管控培训.srt', target_wav=None, target_wav_output=None, name='F:/北森视频下载/首台风机基础浇筑管控培训.mp4', noextname='首台风机基础浇筑管控培训', basename='首台风机基础浇筑管控培训.mp4', ext='mp4', dirname='F:/北森视频下载', shound_del_name=None, detect_language='zh-cn', recogn_type=2, model_name='1.7B', shibie_audio='D:/整個硬盤臨時存放/win-videotrans-v3.66-tiny/tmp/37064/e167d65ac9/首台风机基础浇筑管控培训-1779026328.6889608.wav', remove_noise=False, enable_diariz=True, nums_diariz=0, rephrase=0, fix_punc=True)

1 Replies

这是由于软件路径包含中文和空格,导致 nagisa 分词库无法加载模型文件。

解决方案:

  1. 将整个 pyVideoTrans 软件文件夹移动到纯英文路径(例如 D:\pyvideotrans)下,路径中不能有中文、空格或特殊字符
  2. 删除 tmp 文件夹(如有必要),然后重新启动软件并尝试处理。

注意:当前版本 v3.66 较旧,建议从官网下载最新完整版(推荐 v3.99)并解压到英文路径后再使用。

请查阅相关文档:

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