-
#7184 The model service is temporarily unavailable. Please try again later. (request id: 20260911141459121604303jdmr7UFf)Traceback (most recent call last):...
💬 1[Last reply:3 minutes ago] 这是您使用的 OpenAI 语音识别 API 服务端返回 503 错误导致的，即该 API 服务本身暂时不可用（并非软件 bug）。原因说明：报错 InternalServerError: Error code: 503 - The model service is temporarily unavailable 来自 _openairecognapi.py，说明您配置的 OpenAI 兼容语音识...46.250**9 Posted at: 3 minutes ago -
#7183 Cannot connect to host speech.platform.bing.com:443 ssl:True [SSLCertVerificationError: (1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in ...
💬 1[Last reply:38 minutes ago] 这是 Edge-TTS 在通过代理连接微软服务器时，代理软件的证书（自签名证书）未被系统信任导致的 SSL 证书校验失败。解决方案（按顺序尝试）：强制 Edge-TTS 绕过代理（推荐先试这个）：在软件根目录（即 F:/jianji/win-pyvideotrans-v4.12-0908）下，新建一个空文本文件，命名为：edgetts-noproxy.txt保存后重新执行任务。修改代理软件的证书信...150.107**9 Posted at: 38 minutes ago -
#7182 自动下载模型失败，你可以点击 【查看帮助教程】 了解如何手动下载:...
💬 1[Last reply:47 minutes ago] 核心原因是网络代理的 SSL 证书验证失败（CERTIFICATE_VERIFY_FAILED: self signed certificate in certificate chain），导致从 HuggingFace 下载 Confucius-TTS 模型时连接被阻断。解决方案（按优先级操作）：检查并处理网络代理：你使用了代理工具（如 Clash、V2Ray 等）并开启了 HTTPS 证书劫持...2602**4f38 Posted at: 47 minutes ago -
#7181 配音全部失败 :Noneall_voices={'en-AU-WilliamMultilingualNeural'}...
💬 1[Last reply:1 hour ago] 核心原因是 Edge-TTS 属于微软免费公开接口，你配置了代理（http://127.0.0.1:8899）且 Edge-TTS 对代理连接极为敏感，一旦代理异常或代理被微软风控，会导致该渠道所有请求失败。请按顺序尝试以下操作：强制 Edge-TTS 绕过代理：在软件根目录（F:/jianji/win-pyvideotrans-v4.12-0908/）新建一个名为 edgetts-noproxy...113.71**8 Posted at: 1 hour ago -
#7180 配音全部失败 :Noneall_voices={'en-AU-WilliamMultilingualNeural'}...
💬 1[Last reply:1 hour ago] 这是 Edge-TTS 渠道被限流或被代理拦截导致的配音失败。核心原因：Edge-TTS 是微软免费公开接口，短时间高频请求会被临时封锁；同时你的配置里填了代理 http://127.0.0.1:8899，Edge-TTS 走代理时也极易触发 "Please turn off the clear proxy and try again" 类错误，导致全部配音失败。解决方案（按顺序操作）：降低并发、...113.71**8 Posted at: 1 hour ago -
#7179 配音全部失败 :Noneall_voices={'en-AU-WilliamMultilingualNeural'}...
💬 1[Last reply:1 hour ago] 这是 Edge-TTS 免费接口触发微软限流（403）导致的配音失败，与所选的音色 en-AU-WilliamMultilingualNeural 本身无关。解决方法：打开 菜单 → 工具 → 高级选项 → 字幕配音调整将 EdgeTTS配音渠道配音并发数（同时配音线程数）改为 1将 配音后暂停秒 设为 5 ~ 10保存后重新执行任务补充建议：若配置了代理（你当前填写了 http://127.0....113.71**8 Posted at: 1 hour ago -
#7178 配音全部失败 :Noneall_voices={'en-AU-WilliamMultilingualNeural'}...
💬 1[Last reply:1 hour ago] 这是 Edge-TTS 配音渠道因网络代理或限流导致的失败。底层原因是：使用了 http://127.0.0.1:8899 代理，Edge-TTS 免费接口通过代理时容易被微软拒绝，返回空音频，从而报 None。解决方案（按顺序尝试）：关闭代理：清空主界面对齐控制行右侧的 网络代理 文本框并保存，Edge-TTS 为微软免费接口，国内直连即可，不需要代理。强制 Edge-TTS 绕过代理：在软件根...2602**4f38 Posted at: 1 hour ago -
#7177 Cannot connect to host speech.platform.bing.com:443 ssl:True [SSLCertVerificationError: (1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in ...
💬 1[Last reply:1 hour ago] 这是由于 SSL 证书验证失败导致的，根本原因是你当前网络环境中的代理/防火墙（如公司网络、某些杀毒软件或VPN）对 speech.platform.bing.com 进行了 SSL 中间人拦截，导致 Edge-TTS 无法验证微软服务器的真实证书。解决方案（按顺序尝试）：强制 Edge-TTS 绕过代理 在软件根目录（即 sp.exe 所在文件夹，你的路径是 F:/jianji/win-pyv...2602**4f38 Posted at: 1 hour ago -
#7176 list index out of range:Traceback (most recent call last): File...
💬 1[Last reply:1 hour ago] 这是语音识别阶段内部处理字幕分段时出现的索引越界崩溃（IndexError: list index out of range），发生在 faster-whisper 识别完成后的断句/重排环节。可能原因与解决方向：模型选择不当：你使用的是 distil-large-v3.5 模型，但发音语言选择了简体中文。distil 系列（蒸馏版 Whisper）主要针对英语优化，对中文支持较差，容易在识别后产...2602**4f38 Posted at: 1 hour ago -
#7175 No such file or directory: F:/VideoTrans/models/models--Qwen--Qwen3-ASR-1.7B\model-00001-of-00002.safetensors:Traceback (most recent call last): File...
💬 1[Last reply:2 hours ago] 核心原因：Qwen3-ASR-1.7B 本地模型文件未完整下载（缺少关键权重文件 model-00001-of-00002.safetensors），导致加载失败。解决方案（按步骤操作）：删除残缺模型目录：手动删除 F:/VideoTrans/models/models--Qwen--Qwen3-ASR-1.7B 整个文件夹（可能只下了一半，虽目录看起来存在，但实际不完整）。手动下载完整模型：下载...45.154**4 Posted at: 2 hours ago -
#7174 语音识别成功了,报错无法返回翻译结果,翻译使用的是火山大模型,在设置中翻译测试可以成功,可能的原因是什么...
💬 1[Last reply:3 hours ago] 核心原因：字幕翻译与界面上的“翻译测试”调用的模型类型或参数不同，或翻译过程中触发了模型限制/并发限制，导致批量翻译时失败，而单条测试正常。可能的原因及排查方向：模型名称填写错误或与任务不匹配火山大模型在翻译渠道中应填写纯文本对话模型（如豆包/DeepSeek 等文本模型），不可填写语音识别类或多模态模型。请确认「翻译设置 → 火山大模型」中填写的模型名称是纯文本模型。并发或批量过大导致限流/超时...216.167**4 Posted at: 3 hours ago -
#7173 音画对齐 如果开启视频慢速，是不是只要语音超过时长后，视频才会慢速处理，如果没有超过，不会慢速...
💬 1[Last reply:6 hours ago] 是的，你的理解基本正确，但需要注意细节：视频慢速只会在配音比原字幕时长更长时触发，用于延长画面匹配配音；如果配音没有超出原时长，该句不会做慢速处理。具体策略取决于是否同时启用“音频加速”：仅启用视频慢速：放慢视频画面直至匹配配音时长，但放慢倍数最高不超过设置的 max_video_pts_rate。音频加速 + 视频慢速同时启用：两者协同工作，忽略单项最大倍率限制，声音与画面各承担一半的时间差异。...141.11**1 Posted at: 6 hours ago -
#7172 [WinError 126] The specified module could not be found. Error loading...
💬 1[Last reply:8 hours ago] This WinError 126 when loading caffe2_nvrtc.dll almost always means the underlying NVIDIA CUDA/cuDNN runtime libraries that this DLL depends on are missing or not on the system PATH — not that the DLL...183.80**5 Posted at: 9 hours ago -
#7171 Selecting LLM to correct errors, using the DeepSeek channel, but the key SK was not entered....
💬 1[Last reply:12 hours ago] You enabled "LLM Correction errors" but did not enter the DeepSeek API key, so the LLM correction request fails to authenticate.Fix it in one of these two ways:Enter the DeepSeek key:Go to the top men...37.214**2 Posted at: 12 hours ago -
#7170 CUDA GPU acceleration unavailable. Verify NVIDIA GPU & CUDA installation (Help -> CUDA Help)....
💬 5[Last reply:13 hours ago] Nếu bạn dùng GPU Intel, CUDA hoàn toàn không khả dụng, và phần mềm sẽ tự động chạy trên CPU — không cần bật bất kỳ tùy chọn nào.Để dùng chế độ CPU:Không tích chọn "启用CUDA加速 / Enable CUDA acceleration"...2405**3ff7 Posted at: 13 hours ago -
#7169 Video file selection required...
💬 1[Last reply:15 hours ago] This error means the "Translate Video" task requires please first select an audio or video file — no input file has been chosen before clicking Start.Steps:Click the "Select audio or video" button in ...103.169**1 Posted at: 15 hours ago -
#7168 Error during speech recognition stage[Huggingface_ASR(Built-in)] Automatic model download failed. Click [Help Docs] for manual download instructions:...
💬 1[Last reply:15 hours ago] The core cause is a broken/incomplete model download: the HuggingFace model file transfer was interrupted by the remote peer (peer closed connection without sending complete message body), so the nvid...103.169**1 Posted at: 15 hours ago -
#7167 Error during speech recognition stage[faster-whisper(Built-in)] [Errno 2] No such file or directory: 'E:/video/@@/tmp/17060/e4753aa423/zh-cn.wav':Traceback (most recent call last):...
💬 1[Last reply:16 hours ago] This error is caused by an illegal temporary directory path. Your software root directory is E:/video/@@, and the @@ characters cause FFmpeg/av to fail creating or locating the extracted audio file (z...103.169**1 Posted at: 16 hours ago -
#7166 语音识别阶段出错[阿里FunASR(本地)(内置)] Subprocess Error: regex>=2025.10.22 is required for a normal functioning of this module, but found regex==2023.10.3.Try: `pip install transformers -U` or...
💬 1[Last reply:18 hours ago] 这是 regex 模块版本过低导致的依赖冲突（当前为 2023.10.3，而阿里 FunASR 渠道所需 transformers 要求 >= 2025.10.22）。你是 Windows 预打包版用户（frozen:True），无法直接运行 pip 命令修复依赖，建议按以下顺序处理：确认版本：你的软件目录名为 win-pyvideotrans-v4.00-525，但日志显示版本为 v4.1...113.253**7 Posted at: 18 hours ago -
#7165 Video file selection required...
💬 1[Last reply:19 hours ago] The error "Video file selection required" means no source file was attached before clicking Start. The software requires at least one video/audio file (or a folder, if the Folder checkbox is ticked) t...2402**e709 Posted at: 19 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.