Page 9 BBS.pyVideoTrans.com 能给我deepseek翻译的提示词吗

#7639 能给我deepseek翻译的提示词吗...

[Last reply:6 days ago] DeepSeek 翻译所用的提示词文件位于软件目录下：软件目录/videotrans/prompts/srt/deepseek.txt说明：prompts/srt/ 目录下存放的是各 AI 翻译渠道使用的 SRT 格式提示词模板（如 chatgpt.txt、deepseek.txt 等）。其中 {} 包裹的是变量，软件会自动替换为真实数据，请勿修改或删除。如果你在翻译设置中取消勾选「发送完整字幕」...

2408**11f2 Posted at: 6 days ago

#7638 VieNeu: RuntimeError: Audio rỗng hoặc lỗi ở đoạn 11.Traceback (most recent call last):...

💬 1

[Last reply:6 days ago] The "VieNeu: RuntimeError: Audio rỗng hoặc lỗi ở đoạn 11" error (Vietnamese for "Audio is empty or error at segment 11") originates from the VieNeu TTS engine itself — it returned an empty/invalid aud...

2402**a5d4 Posted at: 6 days ago

#7637 Network connection failedTraceback (most recent call last):...

💬 1

[Last reply:6 days ago] 核心原因：网络连接被中止，导致调用微软翻译接口失败（10053错误）。日志显示当前翻译渠道为 Microsoft（微软翻译）。该渠道为免费在线接口，但国内网络环境不稳定、代理配置不当或微软接口临时不可用，均可能引发该错误。解决方案（按顺序排查）：检查网络代理设置主界面对齐控制(Alignment) 行右侧的代理文本框中，如填写了代理，请确认代理服务已启动、端口正确；如未使用代理，请清空该文本框保...

2408**11f2 Posted at: 6 days ago

#7636 Unable to open file 'model.bin' in model 'C:/pyTrans/models/models--Systran--faster-whisper-medium',Traceback (most recent call last): File...

💬 1

[Last reply:6 days ago] Your faster-whisper-medium model download is incomplete/corrupted — the required model.bin file is missing from C:/pyTrans/models/models--Systran--faster-whisper-medium.The error Unable to open file &...

190.103**2 Posted at: 6 days ago

#7632 No audio file was generated during the listening test.:{'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': 'nverguo.wav', 'filename': 'D:/迅雷云盘/win-pyvideotrans-v4.10/tmp/...

💬 1

[Last reply:6 days ago] 根本原因：您使用了自定义参考音频 nverguo.wav（对应配音渠道 tts_type=1，即 F5-TTS 或同类克隆渠道），但该参考音频未能成功生成配音文件。最可能的原因及排查步骤：参考音频格式不符要求必须为单声道 WAV 格式，时长 3-10 秒，清晰单一人声，无背景噪声，首尾无多余静音。请用工具（如 Audacity）检查并重新导出标准 WAV。参考音频文件名含特殊字符或路径过深您的软...

2409**96d4 Posted at: 6 days ago

#7631 list index out of range:Traceback (most recent call last): File...

💬 1

[Last reply:6 days ago] 这是语音识别后的字幕重新断句（_resegment）模块内部索引越界导致的崩溃，与您的音频、显卡、模型无关，属于软件 bug。处理方案升级到 v4.14（知识库标注最新版本）。v4.14 更新日志明确写有「优化语音/字幕/画面对齐算法」「修复已知bug」，此类 _resegment 越界问题在新版中通常已修正。到 /downpackage 下载 v4.14 补丁包，解压后覆盖到 D:/pyvi...

240e**fe4e Posted at: 6 days ago

#7630 [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'D:/videotrans/win-pyvideotrans-v4.13/tmp/14124/8b698ad969/merged_video.mp4'：D:/videotrans/win-pyvideotrans-v4.13/tmp/14124/8b698ad969/merged_vi...

💬 1

[Last reply:6 days ago] `该错误是因为 merged_video.mp4 文件句柄被另一个进程占用，导致程序在音画对齐阶段（_rate.py 的 _concat_video）无法重命名该文件。常见原因包括：杀毒软件（火绒、360、Windows Defender）正在扫描该临时文件并锁定句柄，或上一次任务的 ffmpeg 进程未完全退出仍在占用文件。解决方法（按顺序尝试）：将软件根目录加入杀毒软件信任白名单：将 D:/v...

125.68**4 Posted at: 6 days ago

#7629 我在使用音视频字幕合并功能时候，只需要原视频和字幕文件合并，没有上传音频文件。但是输出来的视频有不知名的音乐，这是为什么？...

💬 3

[Last reply:6 days ago] "音视频字幕合并"本身不会凭空产生音乐，声音一定来自参与合并的音频源。你未上传音频文件时，输出声音就是原视频自带的原声（含其中的背景音乐）。如果原视频里确实有背景音乐，那它就必然被保留。要"只要画面+字幕、不要任何声音"，操作方法：在软件的"媒体合并(Merge V/A/Srt)"功能中，音频文件一栏不要留空依赖原视频，而是手动指定一段静音音频（自己用 Audacity/ffmpeg 生成一段时长...

60.163**7 Posted at: 6 days ago

#7628 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/authTraceback (most recent call last):...

💬 1

[Last reply:6 days ago] 微软免费翻译接口已更改，你的 v4.03 版本无法继续使用该渠道。解决方案：升级到 v4.14 最新版本（补丁包需完整覆盖，包含 sp.exe、_internal、videotrans 文件夹）。若已是最新版仍报此错，请重新下载一次补丁包覆盖。更推荐改用 DeepSeek 翻译渠道（翻译质量更佳、价格极低）：前往 https://platform.deepseek.com/ 注册并充值（可自定义充...

58.153**8 Posted at: 6 days ago

#7627 翻译字幕阶段出错 [硅基流动] Sorry, your account balance is insufficientTraceback (most recent call last):...

💬 1

[Last reply:7 days ago] 核心原因：硅基流动账户余额不足，服务端返回 HTTP 402 错误，翻译请求被拒绝。解决方案（任选其一）：前往硅基流动官网为你的账户充值，然后重试任务（务必勾选清理已生成，避免使用之前失败的缓存）。更换为其他翻译渠道：菜单 -> 翻译设置，配置其他渠道密钥（如 DeepSeek），并在主界面翻译渠道下拉中切换。补充提醒：若使用 AI 渠道翻译仍报其他解析类错误，可将菜单 -> 工具 ...

240e**4efa Posted at: 7 days ago

#7626 ASR Error [faster-whisper (Local)] Traceback (most recent call last): File...

💬 1

[Last reply:7 days ago] This is caused by insufficient GPU VRAM. The large-v3 model requires roughly 8GB+ of free VRAM, and your GPU ran out of memory during Whisper encoding.Solutions (apply in order):Use a smaller model: c...

202.150**5 Posted at: 7 days ago

#7625 bug提交：批量识别翻译时，出现识别不完整的问题，v4.12正常，v4.13出现这个问题...

💬 3

[Last reply:7 days ago] 批量翻译与单视频翻译的差别之一在于：单视频（一次只选一个文件）会进入单视频交互模式，在每个阶段后暂停，允许您人工校对字幕；而批量翻译不暂停，直接按流程走完。因此"单视频正常、批量不完整"通常不是识别引擎本身的问题，而是批量流程中的资源/缓存/并发因素。可能相关的已知点：批量翻译时多个视频会交叉执行，若在高级选项 → 通用中设置了批量翻译视频时每批数量，或 CPU同时任务数 / GPU同时任务...

141.11**1 Posted at: 7 days ago

#7624 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Den%26tl%3Dhi%26hl%3Dhi%26q%3D%25E0%25A4%2589%25E0%25A...

💬 1

[Last reply:7 days ago] This is a Google Translate rate-limit block (HTTP 429), not a software bug. Google's free endpoint flagged your IP/request pattern as abnormal traffic.Three contributing factors in your config:Google ...

103.169**1 Posted at: 7 days ago

#7623 Error no file named model.safetensors, or pytorch_model.bin, found in directory C:/Working Folders/win-pyvideotrans-v4.12-0913/models/models--Qwen--Qwen3-ASR-1.7B-hf.:Traceback (mo...

💬 1

[Last reply:7 days ago] 核心原因：Qwen-ASR(内置) 的 1.7B 模型文件下载不完整（缺少 model.safetensors 或 pytorch_model.bin 权重文件）。日志中路径 models--Qwen--Qwen3-ASR-1.7B-hf 目录存在但缺少核心权重文件，通常是自动下载中断/失败导致。完全关闭软件。打开目录 C:/Working Folders/win-pyvideotrans-v4....

216.227**2 Posted at: 7 days ago

#7622 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/authTraceback (most recent call last):...

💬 1

[Last reply:7 days ago] This error means the Microsoft (Free) translation channel is broken: Microsoft has changed/disabled the free online translation API endpoint https://edge.microsoft.com/translate/auth, which now return...

85.219**8 Posted at: 7 days ago

#7621 Dubbing failed completely:No audio was received. Please verify that your parameters are correct.all_voices={'vi-VN-HoaiMyNeural'}...

💬 1

[Last reply:7 days ago] The root cause is that Edge-TTS returned no audio, so every dubbing request failed. all_voices={'vi-VN-HoaiMyNeural'} shows the requested voice failed to produce audio, which is almost alway...

113.176**7 Posted at: 7 days ago

#7620 合并阶段出错最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...

💬 1

[Last reply:7 days ago] 核心原因是视频帧率不匹配导致合并失败。日志显示原始视频是 VP9 编码、可变帧率 (VFR)，而输出强制使用 libx264 软编码，帧率不匹配时 FFmpeg 生成的中间文件 novoice.mp4 数据无效，导致最后一步合成时"Invalid data found"。建议按以下方案依次尝试：修改高级选项帧率设置进入菜单 → 工具/选项 → 高级选项 → 【视频输出控制】：可变帧率vfr/...

203.10**4 Posted at: 7 days ago

#7619 合并阶段出错最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...

💬 1

[Last reply:7 days ago] 核心原因是：原始视频编码为 VP9（webm系常见编码），在硬字幕烧录阶段生成的中间文件 novoice.mp4 与目标编码（libx264）不兼容，导致 FFmpeg 读取该中间文件时报 "Invalid data found"。从日志可见：video_codec_name: 'vp9'，分辨率 3840x2160（4K）硬字幕双字幕烧录必须重新编码，而 VP9 → mp4(...

203.10**4 Posted at: 7 days ago

#7618 Error during speech recognition stage[faster-whisper(Built-in)] parallel_for failed: cudaErrorInvalidDevice: invalid device ordinal:Traceback (most recent call last): File...

💬 1

[Last reply:7 days ago] The core issue is that you enabled "CUDA acceleration" but the CUDA runtime cannot find/access the GPU device you are pointing it to — hence cudaErrorInvalidDevice: invalid device ordinal. This is a G...

203.175**3 Posted at: 7 days ago

#7617 Model does not existTraceback (most recent call last):...

💬 1

[Last reply:8 days ago] 这是因为你选择了 OpenRouter 作为语音识别渠道，但没有选择具体的语音识别模型，导致请求发送到 OpenRouter 时模型名称为空，服务端返回 Model does not exist（模型不存在）。从你的日志可以看到：语音识别:OpenRouter, , 发音语言: 越南语，渠道后面是空的，说明模型未选中。解决方案在主界面语音识别(STT Service) 一行，选择 OpenRou...

180.93**2 Posted at: 8 days ago

#7639 能给我deepseek翻译的提示词吗...

#7638 VieNeu: RuntimeError: Audio rỗng hoặc lỗi ở đoạn 11.Traceback (most recent call last):...

#7637 Network connection failedTraceback (most recent call last):...

#7636 Unable to open file 'model.bin' in model 'C:/pyTrans/models/models--Systran--faster-whisper-medium',Traceback (most recent call last): File...

#7632 No audio file was generated during the listening test.:{'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': 'nverguo.wav', 'filename': 'D:/迅雷云盘/win-pyvideotrans-v4.10/tmp/...

#7631 list index out of range:Traceback (most recent call last): File...

#7630 [WinError 32] 另一个程序正在使用此文件，进程无法访问。: 'D:/videotrans/win-pyvideotrans-v4.13/tmp/14124/8b698ad969/merged_video.mp4'：D:/videotrans/win-pyvideotrans-v4.13/tmp/14124/8b698ad969/merged_vi...

#7629 我在使用音视频字幕合并功能时候，只需要原视频和字幕文件合并，没有上传音频文件。但是输出来的视频有不知名的音乐，这是为什么？...

#7628 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/authTraceback (most recent call last):...

#7627 翻译字幕阶段出错 [硅基流动] Sorry, your account balance is insufficientTraceback (most recent call last):...

#7626 ASR Error [faster-whisper (Local)] Traceback (most recent call last): File...

#7625 bug提交：批量识别翻译时，出现识别不完整的问题，v4.12正常，v4.13出现这个问题...

#7624 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Den%26tl%3Dhi%26hl%3Dhi%26q%3D%25E0%25A4%2589%25E0%25A...

#7623 Error no file named model.safetensors, or pytorch_model.bin, found in directory C:/Working Folders/win-pyvideotrans-v4.12-0913/models/models--Qwen--Qwen3-ASR-1.7B-hf.:Traceback (mo...

#7622 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/authTraceback (most recent call last):...

#7621 Dubbing failed completely:No audio was received. Please verify that your parameters are correct.all_voices={'vi-VN-HoaiMyNeural'}...

#7620 合并阶段出错 最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...

#7619 合并阶段出错 最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...

#7618 Error during speech recognition stage[faster-whisper(Built-in)] parallel_for failed: cudaErrorInvalidDevice: invalid device ordinal:Traceback (most recent call last): File...

#7617 Model does not existTraceback (most recent call last):...

Related resource

#7620 合并阶段出错最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...

#7619 合并阶段出错最后一步字幕配音嵌入时出错opening input: Invalid data found when processing input opening input file novoice.mp4. opening input files: Invalid data found when processing inputTraceback (...