-
#7210 F:/VideoTrans/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base does not appear to have a file named speech_tokenizer/config.json. Checkout 'https://huggingface.co/F:/VideoTrans/models...
💬 1[Last reply:2 months ago] 这是 Qwen3-TTS(内置) 的模型文件下载不完整导致的。报错表明模型目录中缺少 speech_tokenizer/config.json 文件。原因:Qwen3-TTS 模型由多个子模块组成(主模型 + speech_tokenizer),自动下载时未能完整获取全部文件。解决方案:删除已下载的不完整模型目录:F:/VideoTrans/models/models--Qwen--Qwen3-T...45.154**4 Posted at: 2 months ago -
#7209 最新版移除合并临近短字幕的话岂不是会TTS合成时参考音频长度不足?...
💬 1[Last reply:2 months ago] 移除的是合并邻近短字幕功能,而非最短语音持续限制。两者作用不同:合并邻近短字幕:把识别出的多条相邻短字幕合并为一条。最短语音持续(毫秒):控制 VAD 切分时,小于该时长的字幕会被尝试合并进相邻字幕。如果你担心参考音频过短导致克隆出错,应通过以下设置控制字幕时长,而非依赖已移除的功能:进入 菜单 → 工具 → 高级选项 → 语音识别参数将 最长语音持续(秒) 设为 6-10将 最短语音持续(毫秒)...203.10**8 Posted at: 2 months ago -
#7208 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory F:/VideoTrans/models/models--k2-fsa--OmniVoice\audio_tokenizer.Traceback (most rec...
💬 1[Last reply:2 months ago] 这是 OmniVoice 内置渠道使用的 audio_tokenizer 模型文件缺失或不完整导致的。软件在指定目录中找不到 model.safetensors 或 pytorch_model.bin,说明模型没有下载成功(或只下载了一部分)。解决办法(手动下载 OmniVoice 模型):打开 HuggingFace 上的 OmniVoice 模型页面:https://huggingface.c...45.154**4 Posted at: 2 months ago -
#7207 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory F:/VideoTrans/models/models--k2-fsa--OmniVoice.Traceback (most recent call last):...
💬 1[Last reply:2 months ago] 这是由于 OmniVoice 模型文件缺失或不完整导致的。软件在 F:/VideoTrans/models/models--k2-fsa--OmniVoice 目录下找不到 model.safetensors 或 pytorch_model.bin,说明该模型未下载完整或下载失败。解决方法:删除现有目录 F:/VideoTrans/models/models--k2-fsa--OmniVoice(...45.154**4 Posted at: 2 months ago -
#7206 Subprocess Error: Error no file named model.safetensors, or pytorch_model.bin, found in directory F:/VideoTrans/models/models--k2-fsa--OmniVoice.:{'text': 'Hello, my dear friend, I...
💬 1[Last reply:2 months ago] 这是因为 OmniVoice 模型文件下载不完整或缺失导致的:软件在 F:/VideoTrans/models/models--k2-fsa--OmniVoice 目录中找不到核心模型文件 model.safetensors 或 pytorch_model.bin,说明模型未成功下载或下载中断。解决方案(按顺序操作):删除已损坏的模型目录彻底删除 F:/VideoTrans/models/mode...45.154**4 Posted at: 2 months ago -
#7205 4.12版本 配音出问题 一直是电流一样的声音 试听那也是电流一样的声音 是怎么回事呀...
💬 1[Last reply:2 months ago] 配音出现电流音,需要先确认是哪一个配音渠道以及是否使用了克隆音色(clone)功能,不同原因处理方式不同。最常见的两种原因:1. 如果您使用了 clone 音色(克隆原始视频说话人音色)系统会从原始视频中自动截取对应时间段的音频作为参考音频。这个截取出来的片段可能存在以下问题,导致配音变成电流/杂音:参考音频时长不合适(太短或太长,TTS 引擎一般要求 3-10 秒)片段中含背景噪声或混入其他说话...45.154**4 Posted at: 2 months ago -
#7204 Dubbing failedNo ref_audio: role='en_female_1.wav',wavfile='F:/VideoTrans/f5-tts/en_female_1.wav':{'text': 'Hello, my dear friend, I hope every day of yours is wonderful and joyful...
💬 1[Last reply:2 months ago] 核心原因:该错误表示所选配音渠道(实际调用的是 Qwen-TTS(内置),见 traceback 中的 _qwenttslocal.py)未能找到参考音频 en_female_1.wav,即文件 F:/VideoTrans/f5-tts/en_female_1.wav 不存在、路径错误或格式不被识别。排查与解决:确认参考音频是否真实存在打开 F:/VideoTrans/f5-tts/ 目录,检查是...45.154**4 Posted at: 2 months ago -
#7203 No audio file was generated during the listening test.:{'text': 'Hello, my dear friend, I hope every day of yours is wonderful and joyful!', 'rate': '+0%', 'role': 'zh_female_cn.wa...
💬 1[Last reply:2 months ago] 核心原因:你选择的配音渠道(tts_type: 1)在试听时未能生成音频文件,导致 DubbingSrtError。同时你使用了参考音频 zh_female_cn.wav(中文音色)去配音英文文本,这本身就是矛盾的——中文克隆音色无法正确合成英文,极易导致该渠道合成失败。请按以下步骤排查:语言与音色匹配:文本是英文(language: en),但你选的参考音频是 zh_female_cn.wav(...144.225**3 Posted at: 2 months ago -
#7202 500: Error code: 500 - {'error': {'message': 'sensitive words detected (request id: 20260912103530480575230jgbvwa9khcDJ5)', 'type': 'new_api_error', 'param': '', 'code': 'sensitive...
💬 1[Last reply:2 months ago] A 500 error with sensitive_words_detected is returned by the AI provider/API gateway itself (a new_api_error type), not by pyVideoTrans. It means the text sent for translation was flagged and rejected...202.150**5 Posted at: 2 months ago -
#7201 This request requires at least $0.50 in balance for audio:Traceback (most recent call last):...
💬 1[Last reply:2 months ago] 这是 OpenRouter 平台余额不足导致的。错误信息明确显示:This request requires at least $0.50 in balance for audio,即使用 OpenRouter 的语音识别接口(用于音频转录)要求账户余额至少达到 $0.50,当前余额不足。解决方案:前往 https://openrouter.ai/settings/credits 为你的 Open...180.93**2 Posted at: 2 months ago -
#7200 Traceback (most recent call last): File...
💬 1[Last reply:2 months ago] This is caused by ffprobe failing to read the video file — the exit status 3221225501 (0xC0000142 / DLL initialization failure on Windows) is triggered by the special characters in your file path, spe...197.132**7 Posted at: 2 months ago -
#7199 Unable to open file 'model.bin' in model 'D:/software/pyvideotrans/win-pyvideotrans-v4.12-0908/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent ...
💬 1[Last reply:2 months ago] 核心原因是 faster-whisper 的 large-v3-turbo 模型文件(model.bin)下载失败或不完整,导致模型无法加载。解决方法:删除不完整的模型目录删除 D:/software/pyvideotrans/win-pyvideotrans-v4.12-0908/models/models--mobiuslabsgmbh--faster-whisper-large-v3-tur...46.151**1 Posted at: 2 months ago -
#7198 配音阶段出错 [Qwen3-TTS(内置)] Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/sougou/win-pyvideotrans-v...
💬 1[Last reply:2 months ago] 核心原因:Qwen3-TTS(内置) 模型文件未下载完整或下载失败。你目录 models/models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice 内缺少模型权重文件(model.safetensors 等),因此加载时报此错。处理步骤:删除残缺模型目录:彻底删除D:/sougou/win-pyvideotrans-v4.112/models/models--Qw...168.158**6 Posted at: 2 months ago -
#7197 CUDA GPU acceleration unavailable. Verify NVIDIA GPU & CUDA installation (Help -> CUDA Help)....
💬 1[Last reply:2 months ago] CUDA acceleration can only work with an NVIDIA GPU, plus a correct CUDA 12.8+ / cuDNN 9.11+ installation, and your software path D:/Program file/... contains a space, which can also cause loading fail...59.25**4 Posted at: 2 months ago -
#7196 :{'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': 'en_female_2.wav', 'filename': 'D:/win-pyvideotrans-v4.12-0908/tmp/9848/listen_voice/5-zh-cn-1789137930.804581.wav', ...
💬 1[Last reply:2 months ago] The underlying cause is that the ONNX model file for the MOSS-TTS-Nano (tts_type 5) dubbing channel was not downloaded or is incomplete. The error is explicit:Load model ...\models\MOSS-TTS-Nano-100M-...50.7**8 Posted at: 2 months ago -
#7195 语音识别阶段出错[openai-whisper(内置)] 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:2 months ago] 核心原因是 openai-whisper 模型文件下载不完整或已损坏,导致加载时 SHA256 校验失败。解决方案:进入软件根目录下的 models/ 文件夹,删除对应的 openai-whisper 模型文件(根据日志使用的是 large-v3,即删除 large-v3.pt)。重新执行任务,让软件自动重新下载模型。若自动下载仍失败,请开启代理(日志中已填 http://127.0.0.1:10...194.233**9 Posted at: 2 months ago -
#7194 语音识别阶段出错[openai-whisper(内置)] 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:2 months ago] 核心原因:openai-whisper 模型的 .pt 文件下载不完整或损坏,导致 SHA256 校验失败。这通常是模型下载过程中网络中断或文件被截断造成的。解决方案(按顺序操作):进入软件目录下的 models/ 文件夹,找到对应的 openai-whisper 模型文件(本次报错使用的是 large-v3,文件名为 large-v3.pt),将其删除。由于原下载地址 openaipublic....194.233**9 Posted at: 2 months ago -
#7193 现在的v4.12 开始视频慢速,如果时间小于视频,是不是就执行慢速了额...
💬 3[Last reply:2 months ago] 暂无法确定。关于"视频慢速导致声音不同步"是否已在 v4.12 修复,我掌握的资料中没有相关记录,需要你提供具体信息以便判断。请补充:你当前使用的具体版本号(软件左上角显示);是"任意视频都不同步"还是"个别视频才出现";不同步的表现(如:画面比声音慢、逐句累积偏移、末尾偏差最大等);该问题出现时的日志(软件目录下 logs/ 文件夹,复制出问题任务对应的报错或异常部分约30行)。补充说明:视频慢...141.11**1 Posted at: 2 months ago -
#7192 No audio file was generated during the listening test.:{'text': 'Hello, my dear friend. I hope your every day is beautiful and enjoyable!', 'rate': '+0%', 'role': 'Serena', 'filena...
💬 1[Last reply:2 months ago] 这是配音(TTS)渠道在试听测试时未能生成音频文件导致的 DubbingSrtError。从日志看,您使用的配音渠道编号为 tts_type: 1,且角色是 Serena、语言 en。可能原因与解决方案:确认配音渠道:tts_type: 1 对应的是某个具体配音渠道。请检查主界面「字幕配音」下拉框中选择的渠道(编号 1 通常不是默认的 Edge-TTS)。如果该渠道需要 API 密钥或本地服务,请...2409**e8e6 Posted at: 2 months ago -
#7191 无效的值或参数:'cp932' codec can't encode character '\u6807' in position 44: illegal multibyte sequenceconcurrent.futures.process._RemoteTraceback:...
💬 1[Last reply:2 months ago] 核心原因有两点,按优先级说明:模型无法下载(根本原因):日志中 ConnectionRefusedError: [WinError 10061] 由于目标计算机积极拒绝,无法连接,是 openai-whisper 在下载模型时无法连接网络。你使用的是 openai-whisper(内置) 渠道,首次使用需从国外网站下载模型,而该站已被屏蔽,必须科学上网或手动下载模型。系统编码错误(表面报错):...125.67**3 Posted at: 2 months 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.