-
#7484 Traceback (most recent call last): File...
💬 1[Last reply:37 minutes ago] 这是因为腾讯翻译服务未开通导致的。报错信息明确显示 Service has not been opened, please open service at Tencent Cloud console,即你的腾讯云账号尚未开通机器翻译(TMT)服务。解决方案:登录腾讯云控制台,开通机器翻译 TMT 服务。确认账号已完成实名认证且有可用额度(新用户通常有免费额度)。开通后回到软件,重新执行翻译任务即可...42.80**8 Posted at: 37 minutes ago -
#7483 Traceback (most recent call last): File...
💬 1[Last reply:50 minutes ago] 核心原因:腾讯翻译服务未开通。报错信息 code:FailedOperation.UserNotRegistered message:Service has not been opened, please open service at Tencent Cloud console 明确表示,你的腾讯云账号尚未开通「机器翻译 TMT」服务。解决方案:登录腾讯云控制台,进入「机器翻译 TMT」产品页面...2408**9184 Posted at: 50 minutes ago -
#7482 Automatic model download failed. Click [Help Docs] for manual download instructions:...
💬 1[Last reply:51 minutes ago] The model download was interrupted by the remote server (peer closed connection without sending complete message body). This is a network stability issue during download of the faster-whisper large-v3...149.34**3 Posted at: 51 minutes ago -
#7481 降噪速度好慢啊,降噪半天还是没有没有好...
💬 1[Last reply:1 hour ago] 降噪功能很慢是正常现象——它走的是 CPU 计算的 ONNX 模型,不走 GPU 加速。这属于软件设计上的限制,无法通过开启 CUDA 解决。可采取的缓解措施(按优先级):跳过降噪,改用「分离人声背景声」:分离功能的效果通常比单纯降噪更好,且可以在主界面 设置更多参数 中勾选,配合「重新嵌入背景声」使用,识别精度更高。两者不必同时开启。提高降噪线程数:进入 菜单 → 工具 → 高级选项 → 通用设...122.189**8 Posted at: 1 hour ago -
#7480 恢复默认设置删那个文件...
💬 1[Last reply:1 hour ago] 删除软件根目录下 videotrans/ 文件夹内的以下4个 JSON 配置文件即可恢复默认设置:params.json(存放用户输入的 API 密钥和偏好设置)cfg.json(存放高级选项及系统设置)codec.json(视频硬解码缓存)ass.json(硬字幕样式缓存)删除后直接双击 sp.exe 即可无痛重建全套出厂配置。请查阅相关文档:常见问题FAQ...122.189**8 Posted at: 1 hour ago -
#7479 Video file selection required...
💬 1[Last reply:1 hour ago] The software is running from a path containing a space and possibly other non-alphanumeric characters (C:/Users/Mr.Dai/Desktop/New folder). The New folder directory name contains a space, which common...113.161**7 Posted at: 1 hour ago -
#7478 Traceback (most recent call last): File...
💬 1[Last reply:2 hours ago] 核心原因是:软件运行环境中的 onnxruntime 包缺失或损坏,导致 faster-whisper 无法加载 VAD(语音活动检测)所需的 onnxruntime 模块,从而报错 ModuleNotFoundError: No module named 'onnxruntime.capi.onnxruntime_pybind11_state'。此外,你当前使用的版本为 v3...45.207**6 Posted at: 2 hours ago -
#7477 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Dzh-cn%26tl%3Dvi%26hl%3Dvi%26q%3D%25E4%25B8%2589%25E7%...
💬 1[Last reply:4 hours ago] This is a Google translate rate-limit (429 / "Too Many Requests") response — Google is temporarily blocking your IP because the free endpoint was queried too frequently (the /sorry/index redirect in t...115.78**9 Posted at: 4 hours ago -
#7476 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Den%26tl%3Dzh-cn%26hl%3Dzh-cn%26q%3Dyou%250ASome%2520o...
💬 1[Last reply:6 hours ago] 这是 Google 翻译免费接口触发了 429 频率限制(Too Many Requests),并且被 Google 判定为异常流量,重定向到了 sorry/index 验证页面。核心原因有二:代理节点 IP 不干净,或被 Google 标记;请求过于频繁。解决方案(按顺序尝试):切换代理节点:你当前使用了代理(URL 中带 google.com/sorry),说明你的 VPN 节点 IP 已被 ...2602**2 Posted at: 6 hours ago -
#7472 文稿匹配打轴为什么在最新版本中没有了?...
💬 4[Last reply:16 hours ago] 该功能入口放到了 菜单---工具/选项下拉菜单里...218.201**7 Posted at: 18 hours ago -
#7475 503 Server Error: Service Unavailable for url: https://edge.microsoft.com/translate/translatetext?from=&to=hi&isEnterpriseClient=falseTraceback (most recent call last):...
💬 1[Last reply:17 hours ago] The core cause is that the built-in Microsoft (free) translation channel is currently returning HTTP 503 Service Unavailable. This is a server-side issue with Microsoft's free web API and is not cause...103.29**5 Posted at: 17 hours ago -
#7474 Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.:Traceback (most recent call last): File...
💬 1[Last reply:17 hours ago] 您使用的是 openai-whisper(内置) 渠道,其模型文件为 .pt 格式(存储于 软件目录/models/ 下)。该报错说明模型文件虽已下载,但文件损坏或不完整,导致 SHA256 校验失败。解决方案:进入软件目录下的 models 文件夹(路径为 C:/Users/g1347/Downloads/win-pyvideotrans-v4.12-0913/models)。找到并删除已损坏的...51.68**3 Posted at: 17 hours ago -
#7473 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Dko%26tl%3Dit%26hl%3Dit%26q%3D%25EB%2596%25A0%25EB%258...
💬 1[Last reply:18 hours ago] This is a Google Translate free-interface rate-limit block (HTTP 429), not a bug in pyVideoTrans itself. Google has temporarily flagged your IP as abnormal traffic and is redirecting requests to its s...151.48**6 Posted at: 18 hours ago -
#7471 model 'qwen2.5:7b-instruct' not foundhttp://127.0.0.1:11434/v1...
💬 1[Last reply:19 hours ago] 核心原因是:你使用的本地 Ollama 服务(http://127.0.0.1:11434/v1)中不存在名为 qwen2.5:7b-instruct 的模型,导致调用返回 404(model not found)。该模型名称与 Ollama 官方命名规范不符。解决方案:打开 CMD/终端,执行 ollama list 查看本地实际已下载的模型名称,核对真实名称(Ollama 中 Qwen2.5 ...120.230**1 Posted at: 19 hours ago -
#7470 model 'qwen2.5:7b-instruct' not foundhttp://127.0.0.1:11434/v1...
💬 1[Last reply:19 hours ago] `这是由于本地 Ollama 服务中并未安装名为 qwen2.5:7b-instruct 的模型,导致请求返回 404 Not Found。解决方案(任选其一):方案 A:安装对应模型打开终端(CMD/PowerShell),执行:ollama pull qwen2.5:7b-instruct等待下载完成后,在软件中重新执行任务。方案 B:改用你本地已有的模型名称在终端执行 ollama list...120.230**1 Posted at: 19 hours ago -
#7469 The checkpoint you are trying to load has model type `qwen3_asr` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or be...
💬 1[Last reply:19 hours ago] 这是由于 Qwen3-TTS(内置) 配音渠道在加载模型时,transformers 库无法识别 qwen3_asr 架构导致的。该问题通常由以下原因引起:模型文件下载不完整或损坏:Qwen3-TTS 和 Qwen3-ASR 的模型文件可能未完整下载。transformers 版本冲突:预打包版内置的 transformers4576 版本与 Qwen3-TTS 所需的架构不匹配。解决方案(按顺序...222.132**0 Posted at: 19 hours ago -
#7468 静音音频幻觉问题怎么解决...
💬 1[Last reply:20 hours ago] 识别出静音片段出现幻觉(重复或无意义文字)是 Whisper 类模型的常见问题,可通过以下方式缓解:提高 VAD 语音阈值:进入 菜单 → 工具 → 高级选项 → 语音识别参数,适当调大 语音阈值,过低会把噪声误判为语音,过高会漏识别。调低非语音阈值:同区域找到 非语音阈值,减小该值可降低幻觉但可能遗漏文字。调整重复惩罚与文本压缩率:增大 重复惩罚、减小 文本压缩率,有利于减少重复和幻觉输出。调小...122.189**2 Posted at: 20 hours ago -
#7467 [Errno 2] No such file or directory: 'nul',Traceback (most recent call last): File...
💬 1[Last reply:20 hours ago] 报错的核心原因:打包程序在启动加载 torch 依赖链时,dill 库尝试访问 Windows 特殊设备文件 nul 失败,根本原因是软件路径中包含了连字符 -(路径为 D:\win-pyvideotrans-v4.12-0913\win-pyvideotrans-v4.12-0913),或与杀毒软件拦截、路径权限有关。解决方案(按优先级依次尝试):修改软件存放路径(最可能的原因)将整个软件文件夹...110.152**8 Posted at: 20 hours ago -
#7466 语音识别阶段出错[faster-whisper(内置)] :Traceback (most recent call last): File...
💬 1[Last reply:22 hours ago] 这是由于内存不足导致的。MemoryError 出现在 numpy 的 FFT 计算(STFT)阶段,说明处理音频时内存(RAM)被耗尽,无法完成频谱变换。核心原因faster-whisper 在处理音频时会进行 STFT 变换,若视频/音频时长过长、文件过大,或系统可用内存不足,就会触发 MemoryError。提示中显示已启用 CUDA 加速,但内存(RAM)与显存(VRAM)是分开的,显存充...2409**9bd7 Posted at: 22 hours ago -
#7465 看到软件可以导入“发音语言SRT”文件,那能不能再增加一个功能:导入转录语言set文件。 因为翻译的功能不可控,手动一条一条修改又太麻烦。 翻译这部分功能允许上传自己修改过的srt文件能节省不少时间和token。希望作者能增加这个功能,非......
💬 1[Last reply:22 hours ago] 软件本身已经支持导入你自行修改好的目标语言(翻译后)SRT 文件,无需新增功能。请按以下规则操作:视频文件所在同级目录下创建 _video_out 文件夹。在 _video_out 内创建与视频同名且带后缀的子文件夹,例如视频为 myvideo.mp4,则创建 _video_out/myvideo-mp4/。将你的字幕按语言代码命名后放入该子文件夹:源语言字幕(发音语言):en.srt(按实际源语...203.10**4 Posted at: 22 hours 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.