#4424 TaskCfgVTT(is_cuda=False, uuid='aaa1808b4c', cache_folder='D:/剪辑工具/tmp/6560/aaa1808b4c', target_dir='D:/视频素材/呋虫胺/_video_

240e:37b* Posted at: 2 hours ago 👁10

语音识别阶段出错 [openai-whisper(本地)] Traceback (most recent call last):
File "urllib\request.py", line 1348, in do_open
File "http\client.py", line 1283, in request
File "http\client.py", line 1329, in _send_request
File "http\client.py", line 1278, in endheaders
File "http\client.py", line 1038, in _send_output
File "http\client.py", line 976, in send
File "http\client.py", line 1448, in connect
File "http\client.py", line 942, in connect
File "socket.py", line 857, in create_connection
File "socket.py", line 845, in create_connection
ConnectionRefusedError: [WinError 10061] 由于目标计算机积极拒绝，无法连接。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 63, in openai_whisper
File "whisper\__init__.py", line 137, in load_model
File "whisper\__init__.py", line 73, in _download
File "urllib\request.py", line 216, in urlopen
File "urllib\request.py", line 519, in open
File "urllib\request.py", line 536, in _open
File "urllib\request.py", line 496, in _call_chain
File "urllib\request.py", line 1391, in https_open
File "urllib\request.py", line 1351, in do_open
urllib.error.URLError:

Traceback (most recent call last):
File "videotrans\task\job.py", line 105, in run
File "videotrans\task\trans_create.py", line 360, in recogn
File "videotrans\recognition\__init__.py", line 272, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 31, in _exec
File "videotrans\recognition\_overall.py", line 73, in _openai
File "videotrans\configure\_base.py", line 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "urllib\request.py", line 1348, in do_open
File "http\client.py", line 1283, in request
File "http\client.py", line 1329, in _send_request
File "http\client.py", line 1278, in endheaders
File "http\client.py", line 1038, in _send_output
File "http\client.py", line 976, in send
File "http\client.py", line 1448, in connect
File "http\client.py", line 942, in connect
File "socket.py", line 857, in create_connection
File "socket.py", line 845, in create_connection
ConnectionRefusedError: [WinError 10061] 由于目标计算机积极拒绝，无法连接。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 63, in openai_whisper
File "whisper\__init__.py", line 137, in load_model
File "whisper\__init__.py", line 73, in _download
File "urllib\request.py", line 216, in urlopen
File "urllib\request.py", line 519, in open
File "urllib\request.py", line 536, in _open
File "urllib\request.py", line 496, in _call_chain
File "urllib\request.py", line 1391, in https_open
File "urllib\request.py", line 1351, in do_open
urllib.error.URLError:
TaskCfgVTT(is_cuda=False, uuid='aaa1808b4c', cache_folder='D:/剪辑工具/tmp/6560/aaa1808b4c', target_dir='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4', source_language='简体中文', source_language_code='zh-cn', source_sub='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4/zh-cn.srt', source_wav='D:/剪辑工具/tmp/6560/aaa1808b4c/zh-cn.wav', source_wav_output='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4/zh-cn.m4a', target_language='英语', target_language_code='en', target_sub='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4/en.srt', target_wav='D:/剪辑工具/tmp/6560/aaa1808b4c/target.wav', target_wav_output='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4/en.m4a', name='D:/视频素材/呋虫胺/0cba840ec578cd4f5a261fbdf33e0791.mp4', noextname='0cba840ec578cd4f5a261fbdf33e0791', basename='0cba840ec578cd4f5a261fbdf33e0791.mp4', ext='mp4', dirname='D:/视频素材/呋虫胺', shound_del_name=None, translate_type=2, tts_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=False, detect_language='zh-cn', recogn_type=1, model_name='tiny', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/视频素材/呋虫胺/_video_out/0cba840ec578cd4f5a261fbdf33e0791-mp4/0cba840ec578cd4f5a261fbdf33e0791.mp4', novoice_mp4='D:/剪辑工具/tmp/6560/aaa1808b4c/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=True, background_music=None, subtitle_type=1, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)

=
system:Windows-10-10.0.17763-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/剪辑工具

1 Replies

Floor #1 DeepSeek reply at 2 hours ago

这是因为你的网络环境无法直接访问 openai-whisper 模型下载服务器（openaipublic.azureedge.net），导致模型文件下载失败，语音识别中断。该问题在中国大陆地区非常常见。

解决方案（按推荐顺序）：

  1. 配置网络代理（如果你有代理服务）
    在主界面 「网络代理地址」 输入框中填写代理（格式如 http://127.0.0.1:10809）。代理生效后，软件即可正常下载模型。

  2. 更换为 faster-whisper(本地) 渠道并手动下载模型（强烈推荐）

    • 切换语音识别渠道为 faster-whisper(本地)。
    • 右侧选择所需模型（如 large-v3 准确度最高，tiny 最小但效果差）。

    • 因 faster-whisper 从 HuggingFace 下载，国内可以手动下载避免网络问题。参考以下详细步骤：

      • 在软件目录的 models 文件夹内创建对应模型文件夹（例如 models--Systran--faster-whisper-large-v3）。
      • 打开 HuggingFace 模型页面（可使用国内镜像 https://hf-mirror.com），将所有 .json / .bin / .txt 文件下载放入文件夹。
      • 完整操作流程请查看文档第 11 节（手动下载 faster-whisper 模型）。
  3. 若依旧坚持使用 openai-whisper
    可手动下载 tiny.pt 模型文件并放入 C:\Users\<你的用户名>\.cache\whisper 目录（如不存在请创建）。下载地址：
    https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt?download=1
    但此方式需要稳定网络，同样建议先通过代理下载。

注意：openai-whisper(本地) 渠道本身速度较慢且网络依赖性强，日常使用推荐改用 faster-whisper(本地)，后者更快且模型管理更友好。

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