-
#7171 Selecting LLM to correct errors, using the DeepSeek channel, but the key SK was not entered....
💬 1[Last reply:22 days 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: 22 days ago -
#7170 CUDA GPU acceleration unavailable. Verify NVIDIA GPU & CUDA installation (Help -> CUDA Help)....
💬 5[Last reply:22 days 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: 22 days ago -
#7169 Video file selection required...
💬 1[Last reply:22 days 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: 22 days 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:22 days 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: 22 days 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:22 days 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: 22 days 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:22 days 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: 22 days ago -
#7165 Video file selection required...
💬 1[Last reply:22 days 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: 22 days ago -
#7164 Authentication Fails, Your api key: ****5d81 is invalidhttps://api.deepseek.com/v1/...
💬 1[Last reply:22 days ago] 这是由于 DeepSeek API 密钥无效导致认证失败，与软件本身无关。原因错误信息 AuthenticationError: 401 - Authentication Fails, Your api key: ****5d81 is invalid 明确指出：您填入的 DeepSeek API 密钥（尾号为 5d81）不被 DeepSeek 服务器认可。解决方案访问 https://platf...180.93**2 Posted at: 22 days ago -
#7163 I’m using PyVideoTrans with the VA + F5-TTS voice cloning workflow.The problem is that the SRT file generated by the tra......
💬 1[Last reply:22 days ago] 可以，通过导入外部 SRT 的方式即可完全跳过自动翻译，同时保留 VA + F5-TTS 的 clone 配音流程，并保留你 SRT 中的原始时间轴。操作步骤：规范文件命名（底层工具对中文/空格/特殊符号兼容差）视频重命名为 myvideo.mp4，你的越南语字幕重命名为 vi.srt，放在与视频同一目录下。手动创建输出目录结构（假设源语言是中文、目标语言是越南语）在视频同级目录创建文件夹：_vi...42.119**9 Posted at: 22 days ago -
#7162 FunASRNano is not registered:Traceback (most recent call last): File...
💬 1[Last reply:22 days ago] 核心原因：软件内置的 funasr 库版本（1.3.1）较旧，其内部注册表中尚未包含 Fun-ASR-Nano-2512 这个新型号，导致加载模型时断言失败。解决方案：暂时更换语音识别渠道，例如改用 faster-whisper(内置) 或 Qwen-ASR(内置)。这是最快恢复使用的办法。如果必须使用 阿里FunASR(内置)，尝试在 FunASR 界面中选择其他已注册的模型，如 parafor...183.23**1 Posted at: 22 days ago -
#7161 Selecting LLM to correct errors, using the DeepSeek channel, but the key SK was not entered....
💬 1[Last reply:23 days ago] The LLM Correction feature (which replaced LLM Re-segmentation in v4.12) requires a valid API Key for the selected AI channel. Since DeepSeek is the default channel and no SK was entered, the correcti...2001**54bc Posted at: 23 days ago -
#7160 想批量翻译字幕后合并到视频里...
💬 7[Last reply:23 days ago] 这说明字幕文件的命名、位置或格式不符合软件的匹配规则。软件批量匹配的核心要求是——视频与字幕文件同名且位于同一文件夹内。请按以下逐项排查：1. 文件名必须完全一致（仅后缀不同）正确：123.mp4 与 123.srt错误：123.mp4 与 123.zh.srt、123_翻译.srt、0001.srt若字幕带的语言后缀是翻译功能自动生成的（如 en.srt），需手动改为与视频同名。2. 必须位于同...156.59**5 Posted at: 23 days ago -
#7159 Subprocess Error: cannot import name 'TensorSpec' from 'safetensors._safetensors_rust' (F:\VideoTrans\_internal\safetensors\_safetensors_rust.cp310-win_amd64.pyd)Traceback (most re...
💬 1[Last reply:23 days ago] 核心原因是 safetensors 库版本不匹配导致 TensorSpec 导入失败。当前日志显示 safetensors 已错误升级（如 0.8.0 等版本移除了 TensorSpec），而 transformers 等旧代码仍在引用，引发 Qwen-ASR(内置) 子进程崩溃。解决方案打开软件目录 F:\VideoTrans，找到 videotrans 文件夹。删除 cfg.json 和 pa...216.183**9 Posted at: 23 days ago -
#7158 Unable to open file 'model.bin' in model 'D:/2-Softwares/PyVidTrans/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last): File...
💬 1[Last reply:23 days ago] The model directory for faster-whisper-large-v3-turbo on your disk is incomplete — model.bin is missing. This is almost always caused by a failed or interrupted model download (large file, unstable ne...212.146**3 Posted at: 23 days ago -
#7157 识别字幕会出现很多同音字，识别不准确的情况...
💬 3[Last reply:23 days ago] 有，v4.12 版本内置了 LLM纠错 功能，专门用于修正识别出的错别字（同音字）、补全标点。使用方式1. 启用在语音识别阶段完成后自动执行，无需单独开启。2. 配置渠道路径：菜单 → 工具 → 高级选项 → 通用设置 → LLM纠错所用AI渠道默认使用 DeepSeek，可切换为其他已配置的 AI 渠道。3. 调整每批字幕行数路径：高级选项 → 通用设置 → LLM纠错每批字幕行数默认 20，该...156.59**5 Posted at: 23 days ago -
#7156 Error during TTS dubbing stage [ChatterBox(Built-in)] CUDA error: device-side assert triggeredCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions....
💬 1[Last reply:23 days ago] This is a CUDA runtime error caused by data going out of range / insufficient resources being passed to the GPU at the moment the ChatterBox model is being loaded onto the device (ve.to(device).eval()...2804**bda2 Posted at: 23 days ago -
#7155 连接超时，请检查网络连接是否稳定:{'text': '你好啊，我亲爱的朋友，希望你的每一天都是美好愉快的！', 'rate': '+0%', 'role': 'Xiaoni(Female/CN)', 'filename': 'C:\\Users\\weike\\AppData\\Local\\Temp/pyvideotrans/0-1789005481.18...
💬 1[Last reply:23 days ago] 这是因为 Edge-TTS 的网络请求走了代理，而代理连接 wss://speech.platform.bing.com 时超时了（报错堆栈中的 _create_proxy_connection + ConnectionTimeoutError 说明请求经过了代理且代理不通或过慢）。Edge-TTS 的接口在国内可直连，通常无需代理。解决方法（按顺序尝试）：强制 Edge-TTS 绕过代理：在软件...117.165**6 Posted at: 23 days ago -
#7154 语音识别阶段出错[faster-whisper(内置)] mkl_malloc: failed to allocate memory,Traceback (most recent call last): File...
💬 1[Last reply:23 days ago] 这是由于物理内存不足导致的：当前未启用 CUDA 加速，large-v3-turbo 模型在 CPU 上加载时需占用数 GB 内存（float32 下更高），加上视频解码、其他软件占用，导致 MKL 内存分配失败。解决方案（按优先级依次尝试）更换更小的模型：把语音识别模型从 large-v3-turbo 换成 small 或 medium（主界面第 2 行语音识别处的模型下拉框）。这是最直接有效的...2409**5012 Posted at: 23 days ago -
#7121 No audio file was generated during the listening test.:{'text': 'नमस्ते, मेरे प्यारे दोस्त, मुझे आशा है कि आपका हर दिन सुंदर और सुखद हो!', 'rate': '+0%', 'role': 'Madhur(Male/IN)',...
💬 37[Last reply:23 days ago] The subtitles filter is still missing from your ffmpeg build. The ffmpeg -filters output you shared earlier did not include lines for subtitles or ass. That means the full tap installation did not tak...103.206**8 Posted at: 24 days ago -
#7153 mkl_malloc: failed to allocate memory,Traceback (most recent call last): File...
💬 1[Last reply:23 days ago] 核心原因：mkl_malloc: failed to allocate memory 错误表示系统内存（RAM）无法提供足够的连续内存来加载 large-v3-turbo 模型，或 MKL 内存分配失败。由于您未启用 CUDA 加速，模型在纯 CPU 模式下运行，large-v3-turbo 需要约 6GB+ 内存，当系统可用内存不足时便会触发此错误。解决方案（按优先级依次尝试）：关闭其他内存占用...2a09**81 Posted at: 23 days 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.