#6865 [ERROR] trk.cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 批量翻译模式原始输入文件名: D:/ike/新建文件夹/cP1.mp4, 输出结果保存到文件夹: D:/ike/cP1-mp4,临时文件夹: E:/ik

116.162.**9 Posted at: 11 hours ago

[ERROR] trk.cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 批量翻译模式
原始输入文件名: D:/ike/新建文件夹/cP1.mp4,
输出结果保存到文件夹: D:/ike/cP1-mp4,
临时文件夹: E:/ike/win-pyvideotrans-v4.08-0802/tmp/19968/f0490057b1
未选 清理已存在
未启用CUDA加速
未选 降噪
已选 识别说话人,最大说话人数量不限制
已选 删除所有标点符号
语音识别:阿里百炼API/Qwen3-ASR, , 发音语言: 英语, 断句方式:LLM重新断句
翻译渠道:DeepSeek,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
未选 配音角色,不进行配音
字幕: 嵌入硬字幕(双) 目标语言在上双字幕
已选 仅输出mp4
[DEBUG] [新进程任务 开始:title='VAD:silero split audio...']
[DEBUG] 新进程任务 参数:kwargs={'input_wav': 'E:/ike/win-pyvideotrans-v4.08-0802/tmp/19968/e26c47abf5/en.wav', 'threshold': 0.5, 'min_speech_duration_ms': 1000, 'max_speech_duration_ms': 5000, 'min_silent_duration_ms': 80}

[DEBUG] [新进程任务 title='VAD:silero split audio...'] 已返回
[DEBUG] [新进程任务 结束:title='VAD:silero split audio...'],耗时16.072334051132202s
[DEBUG] 切分为 1532 个音频片段
[INFO] Starting call to 'videotrans.recognition._qwen3asr.Qwen3A
......
le-mgr.oss-cn-beijing.aliyuncs.com', port=443): Max retries exceeded with url: / (Caused by ConnectTimeoutError(, 'Connection to dashscope-file-mgr.oss-cn-beijing.aliyuncs.com timed out. (connect timeout=3600)'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\job.py", line 35, in run
File "videotrans\task\job.py", line 102, in process_task
File "videotrans\task\_stage_recogn.py", line 62, in recogn
File "videotrans\recognition\__init__.py", line 211, in run
File "videotrans\recognition\_base.py", line 92, in run
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\recognition\_qwen3asr.py", line 36, in _exec
File "dashscope\aigc\multimodal_conversation.py", line 151, in call
File "dashscope\aigc\multimodal_conversation.py", line 249, in _preprocess_messages
File "dashscope\utils\oss_utils.py", line 299, in preprocess_message_element
File "dashscope\utils\oss_utils.py", line 266, in check_and_upload
File "dashscope\utils\oss_utils.py", line 219, in check_and_upload_local
File "dashscope\utils\oss_utils.py", line 93, in upload
File "requests\sessions.py", line 637, in post
File "requests\sessions.py", line 589, in request
File "requests\sessions.py", line 703, in send
File "requests\adapters.py", line 665, in send
requests.exceptions.ConnectTimeout: HTTPSConnectionPool(host='dashscope-file-mgr.oss-cn-beijing.aliyuncs.com', port=443): Max retries exceeded with url: / (Caused by ConnectTimeoutError(, 'Connection to dashscope-file-mgr.oss-cn-beijing.aliyuncs.com timed out. (connect timeout=3600)'))

1 Replies

#1 DeepSeek reply at 11 hours ago

核心原因:语音识别渠道「阿里百炼API/Qwen3-ASR」在向阿里云 OSS 文件服务上传音频时网络连接超时,导致无法完成识别。这通常是网络环境、代理或防火墙配置问题,而非软件本身的 bug。

请按以下步骤排查:

  1. 检查网络连通性:确认本机能否正常访问 dashscope-file-mgr.oss-cn-beijing.aliyuncs.com。可在 CMD 中执行 ping dashscope-file-mgr.oss-cn-beijing.aliyuncs.com,若超时或无响应,说明网络无法直达阿里云。
  2. 关闭或正确配置代理:阿里百炼为国内服务,无需科学上网。如果你设置了全局代理,请暂时关闭,或在软件 菜单 → 设置 → 代理 中清空代理地址并保存;若必须使用代理,请确保上述阿里云域名不被代理拦截。
  3. 确认阿里百炼服务状态:登录阿里百炼控制台,确认已开通 Qwen3-ASR 语音识别服务,且 API Key 填写正确、账户有效。
  4. 更换本地识别渠道:若网络问题短时间无法解决,建议改用本地离线识别渠道,如 faster-whisper(内置),选择 large-v3-turbo 模型,效果稳定且不受网络影响。
  5. 升级版本:当前日志显示为 v4.08,建议升级至最新版 v4.11,可能包含网络重试及连接优化。

请查阅相关文档:

Thinking...
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.

Dondate via ko-fi.com

Related resource