-
#3324 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans-v3.97/tmp/18236/0ad1796be1', target_dir='D:/绿色软件/win-pyvideotrans-v3.97/output/recogn', remove_noise=False, is_separate=Fals...
💬 1[Last reply:3 months ago] 这是由于系统内存(RAM)不足导致 faster-whisper 模型在加载或处理时分配内存失败。解决方案:关闭不必要的程序:关闭浏览器、其他大型软件,释放系统内存。降低模型大小:在语音识别设置中,将模型从 small.en 更换为更小的模型,例如 tiny.en 或 base.en,以减少内存占用。启用 CUDA 加速:如果您的电脑有 NVIDIA 显卡,请安装 CUDA 12.8 和 cuDN...120.211* Posted at: 3 months ago -
#3323 OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/win-pyvideotrans-v3.97/models/models--n...
💬 1[Last reply:3 months ago] 这是由于 HuggingFace 模型文件下载不完整或缺失导致的。软件在 D:/win-pyvideotrans-v3.97/models/models--nvidia--parakeet-ctc-1.1b 目录下找不到模型权重文件(如 pytorch_model.bin 或 model.safetensors)。解决方案:手动下载模型文件:由于 HuggingFace 在国内访问困难,需要手动下...2409:8a38* Posted at: 3 months ago -
#3322 separate vocal and background music:Non-zero status code returned while running ReorderOutput node. Name:'ReorderOutput_token_120' Status Message: C:\a\_work\1\s\onnxruntime\core\f...
💬 1[Last reply:3 months ago] 这是由于显存不足导致的人声分离模型加载失败。升级软件版本:您当前使用的是 v3.86 版本。请先升级到最新版 v3.97,可能已包含优化。检查并释放显存:关闭其他占用 GPU 的程序(如游戏、浏览器、其他 AI 软件)。在任务管理器的“性能”选项卡中,查看 GPU 内存使用情况。调整分离参数:如果升级后问题依旧,在“人声分离”功能中尝试:降低分离模型的复杂度(如果选项可用)。分批次处理较短的音频片...205.185* Posted at: 3 months ago -
#3321 TaskCfg(cache_folder=None, target_dir='E:/PH', remove_noise=False, is_separate=False, detect_language=None, subtitle_language=None, source_language=None, target_language=None, sour...
💬 1[Last reply:3 months ago] The error is caused by the translation model's output exceeding the token limit (8192 completion_tokens). This typically happens when using a local/compatible AI model (like Ollama) to translate a ver...202.150* Posted at: 3 months ago -
#3320 TaskCfg(cache_folder='F:/win-pyvideotrans-v3.97/tmp/27724/68828220d1', target_dir='C:/Users/EWCN/Videos/Character Tool and Pipeline/M/02. CRYENGINE Tutorial - Character Animation P...
💬 1[Last reply:3 months ago] 这是由于视频文件路径中包含空格和特殊字符(冒号)导致的文件复制失败。立即停止:不要继续在当前路径下处理视频。移动源文件:将你的视频文件 02. CRYENGINE Tutorial - Character Animation Pipeline- Export & Import with 3DS Max, Maya, and Blender.mp4 移动到一个路径中不包含中文、空格或特殊符号...47.77* Posted at: 3 months ago -
#3319 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans/tmp/27616/ab7b17491c', target_dir='f:/Users/hp/Desktop/1/_video_out/5-中望3D演示操作要点-PMI和Html-mp4', remove_noise=False, is_separ...
💬 1[Last reply:3 months ago] 这是由于配置的阿里百炼 Qwen3-ASR 语音识别渠道的 API URL 地址错误导致的。解决方案:在软件主界面,点击“语音识别渠道”下拉菜单,选择“阿里百炼 Qwen3-ASR”。检查并修正“API URL”输入框中的地址。正确的地址格式应为阿里百炼平台提供的 API 网关地址,例如 https://dashscope.aliyuncs.com/compatible-mode/v1 或类似格式...66.92* Posted at: 3 months ago -
#3318 TaskCfg(cache_folder='D:/pyvideotrans/tmp/23892/d17b63953e', target_dir='D:/Users/ClaudeSt/Videos/pyvideotrans/recogn', remove_noise=False, is_separate=False, detect_language='auto...
💬 1[Last reply:3 months ago] 这是由于软件打包环境中的 pandas 模块存在循环导入或损坏导致的。请尝试重新下载完整的 pyVideoTrans 软件包(而非补丁包),并解压到新的、路径不含中文和空格的目录中(例如 D:\pyVideoTrans_new)。如果问题依旧,请暂时切换到其他语音识别渠道,例如 faster-whisper 或 openai-whisper 进行识别。请查阅相关文档:FunASR中文识别...182.90* Posted at: 3 months ago -
#3317 The new voice duration doesn't match the original voice....
💬 1[Last reply:3 months ago] 这是由于配音生成的语音时长与原始视频时长不匹配导致的。这是视频翻译配音过程中的核心问题,需要通过软件内置的“音画对齐”功能来解决。解决方案:开启“音画对齐”功能:在软件主界面,点击“高级选项”或“更多设置”,找到“音画对齐”相关配置。选择合适的对齐策略:强制对齐:这是最直接的选项。软件会通过调整配音音频的播放速度(加速或减速),使其总时长强制匹配原始视频的音频时长。这会导致语音音调变化,但能保证时...2001:ee0* Posted at: 3 months ago -
#3316 RuntimeError: Unable to open file 'model.bin' in model 'C:/Users/ACER/AppData/Local/Temp/Rar$EXa5756.47081.rartemp/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'...
💬 1[Last reply:3 months ago] This error occurs because the software is being run directly from inside the compressed archive (.rar file). The temporary extraction path contains special characters ($) and is not a stable location,...88.236* Posted at: 3 months ago -
#3315 TaskCfg(cache_folder='D:/Program Files/win-pyvideotrans-v3.97/tmp/16984/275a38663f', target_dir='D:/绿色软件/win-pyvideotrans-v3.97/output/recogn', remove_noise=False, is_separate=Fals...
💬 1[Last reply:3 months ago] 这是由于系统内存(RAM)不足,导致 faster-whisper 在处理音频时无法分配所需的大数组(875 MiB)而报错。解决方案:降低模型精度:在“语音识别参数”中,将“模型精度”从 float32 改为 int8。这会显著减少内存占用,但可能略微影响识别精度。使用更小的模型:将“模型”从 large-v3 更换为 medium 或 small。小模型对内存和显存的要求更低。关闭说话人分离:...120.211* Posted at: 3 months ago -
#3314 pyimod03_ctypes.install.<locals>.PyInstallerImportError: Failed to load dynlib/dll 'D:\\Program Files\\win-pyvideotrans-v3.97\\_internal\\azure\\cognitiveservices\\speech\\Microsof...
💬 1[Last reply:3 months ago] 这是由于操作系统缺少必要的 VC++ 运行库,导致 Azure TTS 依赖的 DLL 文件无法加载。解决方案:下载并安装微软 VC++ 可再发行组件包。下载地址:https://aka.ms/vs/17/release/vc_redist.x64.exe安装完成后,重启电脑。重新启动 pyVideoTrans 软件。如果问题依旧存在,请确认你使用的是从官网下载的完整版软件包(.7z 格式),而非...120.211* Posted at: 3 months ago -
#3313 HTTPSConnectionPool(host='edge.microsoft.com', port=443): Max retries exceeded with url: /translate/auth (Caused by ProxyError('Unable to connect to proxy', NewConnectionError('<ur...
💬 1[Last reply:3 months ago] 这是由于网络代理配置错误或系统代理设置导致软件无法连接到微软Edge-TTS服务。检查并关闭系统代理:如果你没有主动配置代理,请检查Windows系统设置中的“代理”选项,确保“使用代理服务器”处于关闭状态。检查软件内代理设置:在pyVideoTrans的“设置”->“网络代理”中,确认没有填写任何代理地址。如果填写了,请清空并保存。调整Edge-TTS并发设置:在“高级选项”中,将“同时配...223.73* Posted at: 3 months ago -
#3311 OSError: cannot load library '/Users/dominh/Desktop/video_automation/new_pyvideotrans/.venv/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib': dlopen(/Users/dominh/Des...
💬 1[Last reply:3 months ago] This error occurs because the libsndfile library is missing on your macOS system. The soundfile Python package, which is required by the Qwen-TTS (local) channel, depends on this system library.Soluti...2405:4803* Posted at: 3 months ago -
#3310 Try: `pip install transformers -U` or `pip install -e '.[dev]'` if you're working with git main...
💬 2[Last reply:3 months ago] 是不是从 huggingface 下载的,建议从百度网盘重新下载, huggingface可能不是最新...54.219* Posted at: 3 months ago -
#3309 HTTPSConnectionPool(host='translate.google.com', port=443): Max retries exceeded with url: /m?sl=zh-cn&tl=en&hl=en&q=%E5%85%88%E6%90%AD%E5%BB%BA%E4%B8%BB%E4%BD%93%E6%A1%86%E6%9E%B6...
💬 1[Last reply:3 months ago] 这是由于网络代理配置错误或无法连接导致的。软件尝试通过代理访问 Google 翻译服务,但代理服务器拒绝了连接。解决方案:检查并修正网络代理设置:在软件主界面,点击右上角的“设置”图标(齿轮状)。在“网络代理”部分,确认你填写的代理地址和端口是否正确且有效。如果你没有使用代理,请将“网络代理”设置为“无”或清空地址和端口。如果你在使用代理,请确保代理软件(如 Clash、V2RayN 等)正在运行...106.118* Posted at: 3 months ago -
#3308 [mov,mp4,m4a,3gp,3g2,mj2 @ 0000028460e80400] moov atom not found D:/win-pyvideotrans-v3.97/tmp/14312/9db750aedc/novoice.mp4: Invalid data found when processing input...
💬 3[Last reply:3 months ago] 这是由于视频合成阶段(音画对齐与合成)出现问题导致的。通常与视频编码、临时文件损坏或系统资源有关。解决方案:清理缓存并重试:关闭软件,前往安装目录 D:/win-pyvideotrans-v3.97,删除 tmp/ 文件夹内的所有内容。然后重启软件,重新处理该视频。检查输出目录空间:确保软件输出目录(默认 _video_out/)所在的硬盘有足够的剩余空间。调整对齐策略:在视频翻译任务的“高级选项...240e:358* Posted at: 3 months ago -
#3306 unable to parse the subtitle file,syntax error. using siliconflow trans channel, it is outputting like this:00:03:22:32,......
💬 3[Last reply:3 months ago] 在最新版本中,此设置位于“高级设置”的“翻译参数”部分。在主界面,点击右上角的“设置”图标(齿轮状)。在弹出的设置窗口中,选择左侧的“高级设置”。在“高级设置”页面,找到“翻译参数”区域。将“翻译线程数”的值修改为 1。请查阅相关文档:高级设置各个选项说明...105.246* Posted at: 3 months ago -
#3305 TaskCfg(cache_folder='C:/Users/pc xeon/Downloads/win-pyvideotrans-v3.97/tmp/6616/359389beea', target_dir='C:/Users/pc xeon/Downloads/win-pyvideotrans-v3.97/output/recogn', remove_n...
💬 1[Last reply:3 months ago] This error is caused by a missing or corrupted pytz module within the pre-packaged Windows version of the software, which is triggered when using the FunASR (Local) speech recognition model.Solution:R...1.54* Posted at: 3 months ago -
#3304 ValueError: Unsupported languages: ['Polish']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish']...
💬 1[Last reply:3 months ago] The error is caused by using the Qwen-TTS local channel to generate voice for a language (Polish) that is not currently supported by the model.Solution:Change the TTS channel: Do not use the local "Qw...83.11* Posted at: 3 months ago -
#3303 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/win-pyvideotrans-v3.97/models/models--Qwen--Qwen...
💬 1[Last reply:3 months ago] This error occurs because the required model files for the Qwen3-TTS-12Hz-1.7B-Base model are missing from the specified local directory. The software cannot find the model weights (e.g., model.safete...83.11* Posted at: 3 months ago
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.