Page 5 Latest Topics for bbs.pyvideotrans.com Application started at 2026-03-28 02:39:39 PIL\Image.py:116: RuntimeWarning: The _imaging extension was built for anothe...

#3827 Application started at 2026-03-28 02:39:39 PIL\Image.py:116: RuntimeWarning: The _imaging extension was built for anothe...

[Last reply:5 days ago] 这是由于模型文件下载不完整或损坏导致的。请手动下载并放置模型文件。删除指定目录：按照提示，删除 G:/VideoTrans/Trans/win-pyvideotrans-v3.98-327/models/models--Systran--faster-whisper-large-v3 这个文件夹。手动下载模型：访问模型...

103.172* Posted at: 5 days ago

#3826 TaskCfgVTT(is_cuda=True, uuid='390e4e6473', cache_folder='G:/VideoTrans/Trans/win-pyvideotrans-v3.98-327/tmp/36364/390e4...

💬 1

[Last reply:5 days ago] 这是由于显卡显存不足导致的。错误信息 CUDA failed with error out of memory 表明在使用 faster-whisper(本地) 的 large-v3 模型进行语音识别时，GPU 显存耗尽。解决方案：更换更小的语音识别模型：在主界面的语音识别渠道右侧，将模型从 large-v3 更换为 ...

103.172* Posted at: 5 days ago

#3825 为什么3.98这个，语音识别不出来嘞。...

💬 3

[Last reply:5 days ago] 从日志看，您已正确配置了CUDA加速（is_cuda=True），并选择了faster-whisper(本地)的large-v3模型来识别泰国语（source_language_code='th'）。识别失败最可能的原因是模型未正确加载。请按以下步骤排查：检查模型文件：确认 large-v3 模型文...

103.172* Posted at: 5 days ago

#3824 语音识别阶段出错 [faster-whisper(本地)] 出错了，可能内存或显存不足A child process terminated abruptly, the process pool is not usable anymoreTr...

💬 1

[Last reply:5 days ago] 这是由于内存或显存不足导致语音识别进程崩溃。解决方案：更换更小的识别模型：在语音识别渠道的下拉菜单中，将 large-v3 模型更换为 medium、small 或 base。large-v3 模型对显存/内存要求较高（建议显存 >10GB）。调整高级设置以降低资源占用：点击菜单 -> 工具 -> ...

31.223* Posted at: 5 days ago

#3822 F5TTS._item_task() takes 2 positional arguments but 3 were given...

💬 1

[Last reply:5 days ago] download it and override https://github.com/jianchang512/pyvideotrans/releases/download/v3.98/sp.exe...

79.117* Posted at: 5 days ago

#3823 requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=9880): Max retries exceeded with url: /tt...

💬 1

[Last reply:5 days ago] 这是由于 GPT-SoVITS 本地 TTS 服务未启动或 API 地址配置错误导致的。软件尝试连接 http://127.0.0.1:9880 但被目标计算机拒绝。解决方案：确保 GPT-SoVITS 服务已启动：你需要先独立运行 GPT-SoVITS 项目，并启动其 API 服务。请确保其服务终端窗口未关闭，且正在...

240e:3a1* Posted at: 5 days ago

#649 requests.exceptions.HTTPError: 503 Server Error: Service Unavailable for url: http://127.0.0.1:1188/translate...

💬 4

[Last reply:5 days ago] 问题仍然存在，错误 503 表明 pyVideoTrans 仍然无法连接到您本地的 DeepLX 服务。这通常意味着服务虽然启动了，但并未在正确的地址上响应，或者网络连接被阻止。请按以下步骤排查：验证 DeepLX 服务状态：检查您启动 DeepLX 的命令行窗口，确认它正在运行且没有报错。窗口应显示类似 Listen...

103.219* Posted at: 6 months ago

#3821 separate vocal and background music:cannot import name 'OfflineFireRedAsrCtcModelConfig' from 'sherpa_onnx.lib._sherpa_o...

💬 3

[Last reply:5 days ago] 这是由于软件内置的 sherpa_onnx 模块文件损坏或版本不兼容导致的。此问题通常出现在使用补丁包升级或软件包本身不完整的情况下。解决方案：重新下载完整软件包：前往官方下载地址获取最新的完整软件包（.7z格式），而不是补丁包。全新解压：将下载的完整包解压到一个全新的、路径中不含中文或特殊字符的目录（例如 D:\p...

188.253* Posted at: 5 days ago

#3820 RuntimeError: Calculated padded input size per channel: (6). Kernel size: (7). Kernel size can't be greater than actual ...

💬 1

[Last reply:5 days ago] This error occurs when using the Qwen-TTS (local) voice cloning feature, specifically because the reference audio segment provided for cloning is too short. The...

79.117* Posted at: 5 days ago

#3819 最版版本v3.98-326新增配音渠道小米 tts，如何配置？...

💬 2

[Last reply:5 days ago] https://huggingface.co/mortimerme/repocollect/blob/main/win-pyvideotrans-v3.98-327.7z官网未更新最新版本链接。...

188.253* Posted at: 5 days ago

#3818 videotrans.configure._except.StopRetry: Access denied, please make sure your account is in good standing. For details, s...

💬 1

[Last reply:5 days ago] 这是由于使用了阿里百炼的付费配音渠道（Qwen3-TTS(BailianAPI)），但账户欠费或未开通服务导致的。检查账户状态：访问阿里百炼控制台，确保账户余额充足且服务已开通。更换配音渠道：在软件主界面的“配音渠道”中，切换到其他免费或已配置的渠道，例如：免费渠道：Edge-TTS(免费)本地渠道：Qwen3-TTS...

116.26* Posted at: 5 days ago

#3817 GEMINITTS._item_task() takes from 1 to 2 positional arguments but 3 were given...

💬 2

[Last reply:5 days ago] Bug fixes will be available in a version released several hours later....

42.118* Posted at: 5 days ago

#3816 Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens...

💬 1

[Last reply:5 days ago] 这是由于 OpenAI API 的响应内容过长，超出了模型的最大输出令牌限制（4096个令牌）导致的。解决方案：降低翻译请求的上下文长度：在软件主界面，取消勾选“发送完整字幕”选项。这将改为逐行或小批量发送字幕进行翻译，避免一次性发送过长的上下文。调整高级设置：点击菜单 -> 工具 -> 高级选项，在“字...

183.239* Posted at: 5 days ago

#3815 Application started at 2026-03-27 17:45:16 First searching GPU...[DEBUG] 平台: Windows。正在按优先级检测最佳的 'h264' 编码器: ['nvenc', '...

💬 1

[Last reply:5 days ago] 软件检测到您的系统没有 NVIDIA 显卡，因此无法使用 CUDA 加速。日志显示 NVIDIA_GPU_NUMS=0，这意味着语音识别（使用 faster-whisper 的 large-v3-turbo 模型）将在 CPU 上运行，速度会非常慢。要解决此问题，您有以下几种选择：使用更小的模型：在语音识别渠道的下拉菜...

114.250* Posted at: 5 days ago

#3813 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans/tmp/24544/6ba3294dfb', target_dir='C:/Users/Juno/Desktop/video-t...

💬 1

[Last reply:5 days ago] 该错误是由于您使用的阿里百炼 Qwen3-ASR 语音识别渠道账户欠费或被限制访问导致的。解决方案：检查阿里百炼账户状态：根据错误信息中的链接 https://help.aliyun.com/zh/model-studio/error-code#overdue-payment 登录阿里云控制台，确保您的账户余额充足且服...

23.174* Posted at: 5 days ago

#3812 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans/tmp/24544/8c2ea48b04', target_dir='C:/Users/Juno/Desktop/video-t...

💬 1

[Last reply:5 days ago] This error is caused by a network connection timeout when the Ali Qwen3-ASR service attempts to upload the audio file for processing. The service (dashscope-fil...

158.180* Posted at: 5 days ago

#3811 RuntimeError: {'code': 400, 'message': '未指定参考音频且接口无预设'}...

💬 1

[Last reply:5 days ago] This error occurs because the voice cloning feature (e.g., using a "clone" role in F5-TTS, GPT-SoVITS, or CosyVoice) requires a reference audio clip, but the sy...

103.249* Posted at: 5 days ago

#3810 请求更新支持游戏音频转音色AI...

💬 1

[Last reply:6 days ago] pyVideoTrans 的核心功能是视频/音频的语音识别、字幕翻译和语音合成，其工作流程基于“音频 -> 字幕 -> 翻译 -> 配音”的通用模式。您提到的“游戏音频转音色”并输出特定格式（如ogg）的自动化需求，目前软件无法直接满足。核心原因与现状分析：翻译功能：软件支持字幕翻译。如果您的游戏音频...

205.185* Posted at: 6 days ago

#2432 翻译时调用任务管理器，我的GPU好像没怎么参入工作？...

💬 7

[Last reply:6 days ago] 要彻底卸载 CUDA，请按以下步骤操作：1. 使用 Windows 控制面板卸载程序：打开控制面板 -> 程序和功能。在程序列表中找到所有名称以 “NVIDIA” 开头的项目，特别是：NVIDIA CUDA 12.8.x.x ToolkitNVIDIA CUDA 12.x.x DocumentationNVID...

240e:36a* Posted at: 2 months ago

#1027 videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'prompt_lang: miqi is not supported in version v...

💬 3

[Last reply:6 days ago] 错误原因是 GPT-SoVITS 的 v2 版本 API 不支持你选择的语音角色 miqi。解决方案：在软件主界面，将“配音渠道”从“GPT-SoVITS”切换为其他渠道，例如“Edge-TTS(免费)”。如果必须使用 GPT-SoVITS，请确保你部署的 GPT-SoVITS 服务版本支持 miqi 这个语音角色。你...

240e:3b5* Posted at: 5 months ago

#3827 Application started at 2026-03-28 02:39:39 PIL\Image.py:116: RuntimeWarning: The _imaging extension was built for anothe...

#3826 TaskCfgVTT(is_cuda=True, uuid='390e4e6473', cache_folder='G:/VideoTrans/Trans/win-pyvideotrans-v3.98-327/tmp/36364/390e4...

#3825 为什么3.98这个，语音识别不出来嘞。...

#3824 语音识别阶段出错 [faster-whisper(本地)] 出错了，可能内存或显存不足A child process terminated abruptly, the process pool is not usable anymoreTr...

#3822 F5TTS._item_task() takes 2 positional arguments but 3 were given...

#3823 requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=9880): Max retries exceeded with url: /tt...

#649 requests.exceptions.HTTPError: 503 Server Error: Service Unavailable for url: http://127.0.0.1:1188/translate...

#3821 separate vocal and background music:cannot import name 'OfflineFireRedAsrCtcModelConfig' from 'sherpa_onnx.lib._sherpa_o...

#3820 RuntimeError: Calculated padded input size per channel: (6). Kernel size: (7). Kernel size can't be greater than actual ...

#3819 最版版本v3.98-326新增 配音渠道小米 tts，如何配置？...

#3818 videotrans.configure._except.StopRetry: Access denied, please make sure your account is in good standing. For details, s...

#3817 GEMINITTS._item_task() takes from 1 to 2 positional arguments but 3 were given...

#3816 Could not parse response content as the length limit was reached - CompletionUsage(completion_tokens=4096, prompt_tokens...

#3815 Application started at 2026-03-27 17:45:16 First searching GPU...[DEBUG] 平台: Windows。正在按优先级检测最佳的 'h264' 编码器: ['nvenc', '...

#3813 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans/tmp/24544/6ba3294dfb', target_dir='C:/Users/Juno/Desktop/video-t...

#3812 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans/tmp/24544/8c2ea48b04', target_dir='C:/Users/Juno/Desktop/video-t...

#3811 RuntimeError: {'code': 400, 'message': '未指定参考音频且接口无预设'}...

#3810 请求更新支持游戏音频转音色AI...

#2432 翻译时调用任务管理器，我的GPU好像没怎么参入工作？...

#1027 videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'prompt_lang: miqi is not supported in version v...

Related resource

#3819 最版版本v3.98-326新增配音渠道小米 tts，如何配置？...