Page 66 BBS.pyVideoTrans.com TaskCfgSTT(is_cuda=False, uuid='5c87c4068e', cache_folder='D:/win-pyvideotrans-v3.99/tmp/6748/5c87c4068e', target_dir='D:/win-pyvideotrans-v3.99/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:/win-pyvideotrans-v3.99/output/recogn/凡人修仙传.srt', target_wav=None, target_wav_output=None, name='C:/Users/Administrator/Downloads/凡人修仙传/凡人修仙传.mp4', noextname='凡人修仙传', basename='凡人修仙传.mp4', ext='mp4', dirname='C:/Users/Administrator/Downloads/凡人修仙传', shound_del_name=None, detect_language='zh-cn', recogn_type=3, model_name='paraformer-zh', shibie_audio='D:/win-pyvideotrans-v3.99/tmp/6748/5c87c4068e/凡人修仙传-1776250447.1452572.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)

#4077 TaskCfgSTT(is_cuda=False, uuid='5c87c4068e', cache_folder='D:/win-pyvideotrans-v3.99/tmp/6748/5c87c4068e', target_dir='D:/win-pyvideotrans-v3.99/output/recogn', source_language=Non...

[Last reply:2 months ago] 这是由于内存或显存不足导致阿里FunASR本地模型（paraformer-zh）在语音识别阶段进程崩溃。解决方案：降低资源消耗：在“菜单-工具-高级选项-语音识别参数”中，尝试将“最长语音持续秒数”调小（例如设为3-5秒），以减少单次处理的数据量。检查并关闭其他占用内存/显存的程序，确保有足够资源供软件使用。更换模型：如果上述方法无效，建议改用对资源要求更低的语音识别渠道。对于中文视频，可以尝试：...

39.188* Posted at: 2 months ago

#4076 FileNotFoundError: [Errno 2] No such file or directory: 'C:/Users/Administrator/AppData/Local/Temp/360zip$Temp/360$0/win-videotrans-v3.84/videotrans/cfg.json'...

💬 1

[Last reply:2 months ago] This error occurs because you are trying to run the software directly from within the compressed archive (e.g., a .7z or .zip file), which is not allowed.The error message indicates that the program i...

2408:8207* Posted at: 2 months ago

#4075 Getting available roles, please wait and re-select....

💬 1

[Last reply:2 months ago] This error occurs because the software is being run directly from within a compressed archive (e.g., a .zip or .7z file) or a temporary directory, which prevents it from accessing and saving necessary...

2408:8207* Posted at: 2 months ago

#4074 requests.exceptions.ProxyError: HTTPSConnectionPool(host='translate.google.com', port=443): Max retries exceeded with url: /m?sl=zh-cn&tl=vi&hl=vi&q=%E8%BF%99%E6%AC%BE%E6%89%8B%E6%...

💬 1

[Last reply:2 months ago] 这是由于网络代理设置不正确或代理服务未运行导致的。软件尝试通过代理连接 Google 翻译服务，但代理服务器拒绝了连接。解决方案：检查您的代理客户端（如 VPN、Clash 等）是否正在运行，并确认其本地监听端口号。在主界面的“网络代理地址”文本框中，填入正确的代理地址，格式应为 http://127.0.0.1:端口号（例如 http://127.0.0.1:10808）。如果您没有可用的代理服...

116.16* Posted at: 2 months ago

#4073 TaskCfgSTT(is_cuda=True, uuid='cbf28bc586', cache_folder='E:/ytrans/tmp/10640/cbf28bc586', target_dir='E:/ytrans/output/recogn', source_language=None, source_language_code=None, so...

💬 1

[Last reply:2 months ago] The error KeyError: 'sentence_info' occurs when using the FunASR (local) speech recognition channel. This is typically caused by an issue with the model's output format or a mismatch between...

202.150* Posted at: 2 months ago

#4072 软件3.98版本可以多角色跨语种克隆吗？...

💬 6

[Last reply:2 months ago] 克隆本身就是使用原语音的音色进行配音，是否能够跨语种要视所选配音渠道，qwen-tts(本地)支持中英跨语种，index-tts也支持中英，其他渠道一般都是固定一种...

95.85* Posted at: 2 months ago

#4071 TaskCfgVTT(is_cuda=True, uuid='2bd78abc16', cache_folder='D:/win-pyvideotrans-v3.98-329/tmp/28944/2bd78abc16', target_dir='/ymnas/跨境/tk视频/丰唇膏/已剪/无字幕/西班牙语/0414-1-1-mp4', source_lang...

💬 1

[Last reply:2 months ago] 这是由于显存或内存不足导致的语音识别进程崩溃。解决方案：检查并调整 GPU 设置：确认已正确安装 CUDA 12.8 和 cuDNN 9.x。在软件主界面右上角，取消勾选“二次识别”。同时处理多个视频时，二次识别会占用大量显存。在菜单 -> 工具/选项 -> 高级选项中，将 GPU同时任务数[重启生效] 设为 1，然后重启软件。降低模型和参数以节省资源：将语音识别模型从 base ...

91.199* Posted at: 2 months ago

#4070 This usually indicates a problem with the package or the build environment. Press any key to continue . . ....

💬 1

[Last reply:2 months ago] 这是由于软件安装路径包含中文字符或特殊符号，导致依赖包无法正确加载。解决方案：将软件解压到非系统盘的纯英文路径下，例如 D:\pyVideoTrans。确保路径中不包含中文、空格或特殊符号。重新双击 sp.exe 运行。请查阅相关文档：常见错误与解决方法...

218.8* Posted at: 2 months ago

#4068 TaskCfgSTT(is_cuda=True, uuid='437f3ba732', cache_folder='D:/Software/pyvideotrans/tmp/50340/437f3ba732', target_dir='D:/Software/pyvideotrans/output/recogn', source_language=None,...

💬 1

[Last reply:2 months ago] 这是由于显存或内存不足导致的。使用 faster-whisper(本地) 的 large-v3 模型进行语音识别时，该模型需要较大的显存（建议10GB以上）或内存（建议16GB以上）。错误信息显示进程池被意外终止，这是资源耗尽的典型表现。解决方案：使用更小的模型：在主界面的语音识别渠道右侧，将模型从 large-v3 更换为 medium、small 或 base。large-v3 模型对硬件要求...

146.19* Posted at: 2 months ago

#4067 TaskCfgSTT(is_cuda=True, uuid='015483d275', cache_folder='E:/ytrans/tmp/3636/015483d275', target_dir='E:/ytrans/output/recogn', source_language=None, source_language_code=None, sou...

💬 1

[Last reply:2 months ago] This error is caused by insufficient GPU memory (VRAM) when using the faster-whisper model with CUDA acceleration.Solutions:Disable "Secondary Recognition": If you have "Secondary Recognition" enabled...

202.150* Posted at: 2 months ago

#4066 TaskCfgVTT(is_cuda=True, uuid='70961f1ce3', cache_folder='D:/pyvideotrans/tmp/18196/70961f1ce3', target_dir='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidenta...

💬 1

[Last reply:2 months ago] 这是由于显存或内存不足导致的。错误信息明确指出“可能内存或显存不足 [GPU0]”，并且使用了 large-v3-turbo 模型，该模型对显存要求较高。解决方案如下：使用更小的模型：在语音识别渠道的下拉菜单中，将模型从 large-v3-turbo 更换为 medium、small 或 base。large-v3 系列模型最低需要约 10GB 显存。调整高级设置以降低显存占用：点击菜单 -&g...

114.249* Posted at: 2 months ago

#4065 TaskCfgVTT(is_cuda=True, uuid='3d958ad971', cache_folder='D:/pyvideotrans/tmp/6324/3d958ad971', target_dir='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidental...

💬 1

[Last reply:2 months ago] 这是由于显存或内存不足导致语音识别进程崩溃。从日志可见，你使用了 faster-whisper(本地) 的 large-v3-turbo 模型，并启用了 CUDA 加速 (is_cuda=True)，但进程池被意外终止，提示可能内存或显存不足。解决方案：降低模型大小：在语音识别下拉菜单中，将模型从 large-v3-turbo 更换为更小的模型，例如 medium 或 small。large-v3...

206.237* Posted at: 2 months ago

#4064 piper-tts的国内下载地址...

💬 1

[Last reply:2 months ago] Piper-TTS 的模型文件需要从 GitHub 或 HuggingFace 下载，国内访问可能不稳定。你可以尝试以下方法获取模型：手动下载模型文件：访问 Piper-TTS 的 GitHub 仓库发布页：https://github.com/rhasspy/piper/releases找到并下载名为 piper_voice-en-gb-alan-low.tar.gz 或你所需语言/音色的 .t...

182.107* Posted at: 2 months ago

#4063 400 The plain HTTP request was sent to HTTPS port400 Bad RequestThe plain HTTP request was sent to HTTPS portcloudflare:......

💬 1

[Last reply:2 months ago] 这是由于配置的本地大模型 API 地址使用了 HTTP 协议，但服务端实际要求 HTTPS 协议导致的。检查 API 地址：请前往菜单 -> 翻译设置 -> 本地大模型设置，检查你填写的 API 地址。修正协议：错误信息显示 The plain HTTP request was sent to HTTPS port，这表明你配置的地址可能是 http://...，但服务端（例如 Cl...

240e:354* Posted at: 2 months ago

#4062 ValueError: The elements of the batch contain different keys. Cannot batch them ({'attention_mask', 'is_last', 'input_features'} != {'attention_mask', 'is_last', 'input_features', ...

💬 1

[Last reply:2 months ago] 这是由于使用了 FunASR 语音识别渠道时，模型加载或数据处理过程中出现了内部错误。解决方案：切换语音识别渠道：暂时不要使用 “FunASR中文识别” 渠道。建议切换回更稳定的渠道，例如：对于中文视频：使用 qwen-asr(本地)。对于多语言或英文视频：使用 faster-whisper(本地) 并选择 large-v3 模型。检查模型文件：如果你坚持使用 FunASR，此错误可能意味着模型文...

52.197* Posted at: 2 months ago

#4061 无效的值或参数：The upstream Gradio app has raised an exception but has not enabled verbose error reporting. To enable, set show_error=True in launch().: Traceback (most recent call last):...

💬 1

[Last reply:2 months ago] 这是在使用 OmniVoice-TTS 配音渠道时，其外部 API 服务（Gradio 应用）内部发生了错误，但未返回详细错误信息。检查 OmniVoice-TTS 服务状态：确保你已正确部署并启动了 OmniVoice-TTS 的 API 服务（通常是一个在终端中运行的 WebUI 或服务端程序）。该服务必须处于运行状态，且 pyVideoTrans 中配置的 API 地址（如 http://1...

95.85* Posted at: 2 months ago

#4060 aiohttp.client_exceptions.ConnectionTimeoutError: Connection timeout to host wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4...

💬 1

[Last reply:2 months ago] 这是由于 Edge-TTS 配音渠道的网络连接超时导致的。微软的服务可能因网络不稳定或并发请求过高而触发限流。解决方案：降低并发请求：在软件顶部菜单栏，点击工具/选项 -> 高级选项，找到【字幕配音调整】区域。将并发配音线程数设置为 1。将配音后暂停秒设置为 5 或更高。将 EdgeTTS配音渠道配音并发数设置为 1。检查网络连接：确保你的网络环境可以稳定访问微软的服务。如果使用...

112.111* Posted at: 2 months ago

#4059 A child process terminated abruptly, the process pool is not usable anymore Traceback (most recent call last): File "videotrans\task\_only_one.py", line 113, in run File "video...

💬 1

[Last reply:2 months ago] 这是由于启用了“视频慢速”功能，在处理过程中子进程意外终止导致进程池崩溃。解决方案：取消“视频慢速”：在主界面的“同步对齐”区域，取消勾选“视频慢速”选项。这是最直接的解决方法，因为该功能会生成大量临时文件并增加处理复杂度。检查文件路径：确保你的视频文件路径（包括软件安装路径）不包含中文或特殊符号。建议将软件移动到如 D:\pyVideoTrans 这样的纯英文路径，并将视频文件也放在浅层英文目录...

95.85* Posted at: 2 months ago

#4058 TaskCfgSTT(is_cuda=True, uuid='98d9d0f1de', cache_folder='/home/amu/pyvideotrans/tmp/443031/98d9d0f1de', target_dir='/home/amu/pyvideotrans/output/recogn', source_language=None, so...

💬 1

[Last reply:2 months ago] 这是由于自定义语音识别 API（VibeVoice-ASR）服务未返回有效数据，且代码中存在一个变量未定义的错误。检查 VibeVoice-ASR 服务状态：确保你部署的 VibeVoice-ASR API 服务正在运行且可访问。在终端中检查其运行状态，并尝试直接向 API 地址（例如 http://127.0.0.1:5000）发送请求，确认其能正常返回识别结果。检查 API 配置：在 pyVi...

178.128* Posted at: 2 months ago

#4057 TaskCfgSTT(is_cuda=True, uuid='d60f6dd9b6', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/27268/d60f6dd9b6', target_dir='F:/AI/win-pyvideotrans-v3...

💬 1

[Last reply:2 months ago] 这是由于显存或内存不足导致的。在使用 openai-whisper(本地) 的 large-v3-turbo 模型进行语音识别时，该模型对显存/内存需求较高，导致子进程崩溃。解决方案：使用更小的模型：在主界面的语音识别渠道下拉菜单中，将模型从 large-v3-turbo 更换为 medium、small 或 base。调整高级设置以降低资源占用：进入菜单 -> 工具/选项 -> 高...

149.88* Posted at: 2 months ago

#4077 TaskCfgSTT(is_cuda=False, uuid='5c87c4068e', cache_folder='D:/win-pyvideotrans-v3.99/tmp/6748/5c87c4068e', target_dir='D:/win-pyvideotrans-v3.99/output/recogn', source_language=Non...

#4076 FileNotFoundError: [Errno 2] No such file or directory: 'C:/Users/Administrator/AppData/Local/Temp/360zip$Temp/360$0/win-videotrans-v3.84/videotrans/cfg.json'...

#4075 Getting available roles, please wait and re-select....

#4074 requests.exceptions.ProxyError: HTTPSConnectionPool(host='translate.google.com', port=443): Max retries exceeded with url: /m?sl=zh-cn&tl=vi&hl=vi&q=%E8%BF%99%E6%AC%BE%E6%89%8B%E6%...

#4073 TaskCfgSTT(is_cuda=True, uuid='cbf28bc586', cache_folder='E:/ytrans/tmp/10640/cbf28bc586', target_dir='E:/ytrans/output/recogn', source_language=None, source_language_code=None, so...

#4072 软件3.98版本可以多角色跨语种克隆吗？...

#4071 TaskCfgVTT(is_cuda=True, uuid='2bd78abc16', cache_folder='D:/win-pyvideotrans-v3.98-329/tmp/28944/2bd78abc16', target_dir='/ymnas/跨境/tk视频/丰唇膏/已剪/无字幕/西班牙语/0414-1-1-mp4', source_lang...

#4070 This usually indicates a problem with the package or the build environment. Press any key to continue . . ....

#4068 TaskCfgSTT(is_cuda=True, uuid='437f3ba732', cache_folder='D:/Software/pyvideotrans/tmp/50340/437f3ba732', target_dir='D:/Software/pyvideotrans/output/recogn', source_language=None,...

#4067 TaskCfgSTT(is_cuda=True, uuid='015483d275', cache_folder='E:/ytrans/tmp/3636/015483d275', target_dir='E:/ytrans/output/recogn', source_language=None, source_language_code=None, sou...

#4066 TaskCfgVTT(is_cuda=True, uuid='70961f1ce3', cache_folder='D:/pyvideotrans/tmp/18196/70961f1ce3', target_dir='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidenta...

#4065 TaskCfgVTT(is_cuda=True, uuid='3d958ad971', cache_folder='D:/pyvideotrans/tmp/6324/3d958ad971', target_dir='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidental...

#4064 piper-tts的国内下载地址...

#4063 400 The plain HTTP request was sent to HTTPS port400 Bad RequestThe plain HTTP request was sent to HTTPS portcloudflare:......

#4062 ValueError: The elements of the batch contain different keys. Cannot batch them ({'attention_mask', 'is_last', 'input_features'} != {'attention_mask', 'is_last', 'input_features', ...

#4061 无效的值或参数：The upstream Gradio app has raised an exception but has not enabled verbose error reporting. To enable, set show_error=True in launch().: Traceback (most recent call last):...

#4060 aiohttp.client_exceptions.ConnectionTimeoutError: Connection timeout to host wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4...

#4059 A child process terminated abruptly, the process pool is not usable anymore Traceback (most recent call last): File "videotrans\task\_only_one.py", line 113, in run File "video...

#4058 TaskCfgSTT(is_cuda=True, uuid='98d9d0f1de', cache_folder='/home/amu/pyvideotrans/tmp/443031/98d9d0f1de', target_dir='/home/amu/pyvideotrans/output/recogn', source_language=None, so...

#4057 TaskCfgSTT(is_cuda=True, uuid='d60f6dd9b6', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/27268/d60f6dd9b6', target_dir='F:/AI/win-pyvideotrans-v3...

Related resource