-
#7796 选择LLM纠正错误，使用智谱AI渠道，但未填写密钥SK.可在菜单-工具/选项-高级选项-LLM纠错渠道中切换...
120.85**3 Posted at: 1 hour ago -
#7795 翻译字幕阶段出错 [兼容AI/本地模型] prediction aborted, token repeat limit reachedTraceback (most recent call last):...
💬 1[Last reply:1 hour ago] 这是本地部署的小模型在翻译时陷入重复输出死循环，导致触发了本地推理服务的「token 重复限制」保护而中断。解决方案：精简本地模型提示词（首选）本地部署的小模型（如 7B 级）指令跟随能力弱，长提示词+附带完整字幕极易导致模型陷入重复。打开 D:/RUANJIAN/win-pyvideotrans-v4.14/videotrans/prompts/srt/localllm.txt（你已勾选发送完整...120.85**3 Posted at: 1 hour ago -
#7794 翻译字幕阶段出错 [Google(免费)] Connection reset, network may be unstableTraceback (most recent call last):...
💬 1[Last reply:2 hours ago] 核心原因是 Google 翻译渠道网络连接失败（Connection reset），当前使用的代理 http://127.0.0.1:7890 不稳定或被 Google 拒绝。此外日志显示程序实际已回退到微软翻译（_microsoft.py），但同样连接被重置。解决方案（按优先级）：更换/检查代理节点：确认本地代理服务（7890端口）正在运行，且节点可正常访问 Google。切换更干净的节点，避免...160.22**4 Posted at: 2 hours ago -
#7793 Video file selection required...
💬 1[Last reply:2 hours ago] No video or audio file has been selected yet — the "Select Video/Audio" field is empty, so the Start button cannot proceed.Solution:Click the "Select Video/Audio" button at the top-left of the main wi...79.27**1 Posted at: 2 hours ago -
#7792 Each line must contain 3 parts separated by '#': audio_name.wav#audio_text#lang_code...
💬 1[Last reply:3 hours ago] The reference-audio line format you wrote (audio_name.wav#audio_text#lang_code) is not the format pyVideoTrans accepts. The correct format has only 2 parts, separated by a single #:filename.wav#the sp...187.40**7 Posted at: 3 hours ago -
#7788 选择LLM纠正错误，使用智谱AI渠道，但未填写密钥SK.可在菜单-工具/选项-高级选项-LLM纠错渠道中切换...
💬 7[Last reply:3 hours ago] 这段日志与上一条完全相同，仍然只是软件正常启动的初始化记录，没有任何报错：硬件编码器 h264_nvenc / hevc_nvenc 检测通过，GPU 检测到 1 张 N 卡，线程池按 12 核 CPU 配置（MAX_CPU_PROCESS=4, MAX_GPU_PROCESS=1）。唯一提示是 无法连接 huggingface.co, 使用镜像替换: hf-mirror.com，属正常网络提示，...120.85**3 Posted at: 4 hours ago -
#7790 Each line must contain 3 parts separated by '#': audio_name.wav#audio_text#lang_code...
💬 1[Last reply:3 hours ago] This format audio_name.wav#audio_text#lang_code is not a valid reference-audio entry format, and combined with your clone requirement it will fail.The correct reference-audio format requires only 2 pa...187.40**7 Posted at: 3 hours ago -
#7789 Network connection failed:Traceback (most recent call last): File...
💬 1[Last reply:3 hours ago] Core cause: This is a Gemini API connection failure. The error RemoteProtocolError: Server disconnected without sending a response combined with APIConnectionError means your network could not establi...187.40**7 Posted at: 3 hours ago -
#7787 indextts Service must be deployed and running before useself.api_url='http://127.0.0.1:7860'...
💬 1[Last reply:4 hours ago] The error [WinError 10061] No se puede establecer una conexión... (Connection refused) indicates the software cannot connect to your Index-TTS service at http://127.0.0.1:7860. Index-TTS is a self-dep...181.172**3 Posted at: 4 hours ago -
#7786 Network connection failedTraceback (most recent call last):...
💬 1[Last reply:4 hours ago] The root cause is a network connection failure when calling the Gemini AI translation API. The error Server disconnected without sending a response means the request to Google's Gemini endpoint could ...187.40**7 Posted at: 4 hours ago -
#7785 [openrouter] Cannot connect to https://openrouter.ai/api/v1. Check network access or verify local server deployment.Connection error.:Traceback (most recent call last):...
💬 1[Last reply:5 hours ago] The error WinError 10061 (connection actively refused) with the traceback showing httpcore\_sync\http_proxy.py indicates that the connection to https://openrouter.ai/api/v1 is being routed through a p...187.40**7 Posted at: 5 hours ago -
#7784 Network connection failed:Traceback (most recent call last): File...
💬 1[Last reply:6 hours ago] This is a network connectivity failure when calling the Gemini translation API. The error [WinError 10053] An established connection was aborted by the software in your host machine indicates the loca...187.40**7 Posted at: 6 hours ago -
#7783 高级选项里，我主要翻译韩文视频，怎么设置正确率最高...
💬 1[Last reply:6 hours ago] 翻译韩文视频时，提升“正确率”的关键不是单一参数，而是语音识别渠道/模型选择 + 字幕切分参数 + 翻译渠道三者配合。按以下设置最稳妥：1. 语音识别渠道（最关键）首选：faster-whisper(内置)，模型选 large-v3（准确度最高）或 large-v3-turbo（速度与质量兼顾）备选：openai-whisper(内置) + large-v3若有 N 卡，务必勾选启用CUDA加速2...103.151**5 Posted at: 6 hours ago -
#7782 ...
💬 1[Last reply:6 hours ago] 这是模型文件下载不完整或缺失导致的。根据你提供的文件目录截图，你正在使用 F5-TTS(内置) 配音渠道，但 models/models--SWivid--F5-TTS/F5TTS_v1_Base 目录下的模型文件下载失败或未下载完全。解决方案：手动下载模型访问官方模型下载地址：https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_v1_Base...103.151**5 Posted at: 6 hours ago -
#7781 No audio file was generated during the listening test.self=OmniVoice(uuid=None, proxy_str=None, last_down_time=0, tts_type=3, len=1, language='de', play=True, volume='+33%', rate='...
💬 1[Last reply:7 hours ago] The OmniVoice TTS channel failed to produce any output audio file during the listening test — meaning the model either did not load correctly or the voice-cloning reference was rejected, so no wav was...42.1**0 Posted at: 7 hours ago -
#7772 下的有模型models--Qwen--Qwen3-ASR-1.7B 为什么还要再新建一个文件夹models--Qwen--Qwen3-ASR-1.7B-hf 再去下模型 怎么指定...
💬 8[Last reply:10 hours ago] 4.12后改用qwen的hf版模型，所以需要重新下载，不能简单修改文件夹名称替换。Qwen3-ForcedAligner-0.6B 是在识别后重新断句用的模型，同样都改为了hf版hf版是qwen针对transformers推理的单独版本...140.207**4 Posted at: 15 hours ago -
#7780 翻译字幕阶段出错 [Gemini AI] User location is not supported for the API use.Traceback (most recent call last):...
💬 1[Last reply:11 hours ago] 核心原因：Gemini AI 接口不支持你当前所在的 IP 地区（User location is not supported for the API use），即节点地区不被 Google 允许。解决方案：更换网络代理节点，切换到 Gemini 支持的地区（如美国、日本等），并确保代理全局生效、端口（你填的 http://127.0.0.1:7897）正确。若换节点后仍不行，改用其他无需地区限制...103.151**5 Posted at: 11 hours ago -
#7779 Connection reset, network may be unstableTraceback (most recent call last):...
💬 1[Last reply:11 hours ago] 这是网络连接问题，微软免费翻译接口在请求时被服务器强制断开（WinError 10054）。通常由网络不稳定、代理配置异常、或微软接口临时限流导致。解决方案（按顺序尝试）检查并清空代理设置：查看主界面「对齐控制」行右侧的代理文本框。如果你填写了代理地址（如 http://127.0.0.1:10808），请临时清空它再重试。填写了无效或不通的代理会导致所有网络请求失败。更换翻译渠道：微软免费翻译接...101.71**1 Posted at: 11 hours ago -
#7778 [Clone-Voice] Service must be deployed and running before useself.api_url='http://127.0.0.1:9988'...
💬 1[Last reply:11 hours ago] The core cause: you selected the clone-voice(LocalAPI) TTS channel, but that local service is not running (or not deployed). The error WinError 10061 No connection could be made because the target mac...175.100**4 Posted at: 11 hours ago -
#7777 Unsupported language_id 'km'. Supported languages: ar, da, de, el, en, es, fi, fr, he, hi, it, ja, ko, ms, nl, no, pl, pt, ru, sv, sw, tr, zhTraceback (most recent call last):...
💬 1[Last reply:12 hours ago] The root cause is that you selected the ChatterBox (Built-in) TTS channel for dubbing, but ChatterBox does not support Khmer (km). Its supported languages are only: ar, da, de, el, en, es, fi, fr, he,...175.100**4 Posted at: 12 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.