#5646

Whisper.NET 渠道配置文件缺失。您选择的模型中 .bin 格式的 ggml 模型不存在于 models/ 目录下。

解决方案：

1. 安装依赖（源码部署用户）：在软件根目录下执行 uv sync --extra dotnet
2. 下载模型文件：从官网或 HuggingFace 下载 .bin 格式的 Whisper 模型（例如 ggml-large-v3.bin），放入 models/ 文件夹
3. 检查模型选择：在软件主界面“ASR Channel”中选择 Whisper.Net 后，确认下拉框中的模型名称与已下载的文件名一致（例如名称不含 .bin 后缀）

若仍无法解决，请提供日志文件（logs/ 目录下最新 .log 文件内容）和软件版本号。

请提供该错误消息的文本内容（直接复制粘贴报错信息），或者提供 logs/ 文件夹下最新的日志文件中的末尾20行，同时告知软件版本号，以便我准确分析问题原因。

elf.cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 单视频模式
原始输入文件名: //192.168.1.109/共享素材库/运营文件夹/袁雨欣/三角置物架/下载 (5).mp4,
输出结果保存到文件夹: //192.168.1.109/共享素材库/运营文件夹/袁雨欣/三角置物架/13/下载 (5)-mp4,
临时文件夹: D:/win-pyvideotrans-v4.03-0626/tmp/200/df6d2e7464
已选 清理已存在
已选 启用CUDA加速
未选 降噪
语音识别:Qwen-ASR(本地内置), model_name: 1.7B, 发音语言: 简体中文, 断句方式:默认断句
翻译渠道:Google(免费),原始语言:简体中文,目标语言:th, 已选 发送完整字幕
未选 配音角色，不进行配音
字幕: 嵌入硬字幕
已选 仅输出mp4
代理地址:
[DEBUG] The file info after process:result={'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 1080, 'height': 1920, 'time': 6500, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
[DEBUG] runffmpeg:cmd=['ffmpeg', '-hide_banner', '-nostdin', '-ignore_unknown', '-threads', '0', '-y', '-fflags', '+genpts', '-i', '//192.168.1.109/共享素材库/运营文件夹/袁雨欣/三角置物架/下载 (5).mp4', '-an', '-c:v', 'copy', 'novoice.mp4']

2026-07-06 10:02:18,260 - modelscope - WARNING - We can not confirm the cached file is for revision: master
[DEBUG] 开始使用 [silero] VAD处理
[DEBUG] [silero语音识别参数],min_speech_duration_ms:3000ms,max_speech_duration_ms:_max_speech=5000ms,min_silent_duration_ms:140ms, threshold:0.5
[DEBUG] [新进程任务 开始:title='VAD:silero split audio...']
[DEBUG] 新进程任务 参数:kwargs={'input_wav': 'D:/win-pyvideotrans-v4.03-0626/tmp/200/df6d2e7464/zh-cn.wav', 'threshold': 0.5, 'min_speech_duration_ms': 3000, 'max_speech_duration_ms': 5000, 'min_silent_duration_ms': 140}

[DEBUG] [新进程任务 title='VAD:silero split audio...'] 已返回
[ERROR] VAD:silero split audio...,None
Traceback (most recent call last):
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: None
[DEBUG] [新进程任务 结束:title='VAD:silero split audio...']，耗时4.0491485595703125s
[ERROR] VAD 处理失败 None
Traceback (most recent call last):
File "videotrans\recognition\_base.py", line 179, in _vad_split
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: None
[ERROR] 单视频模式翻译失败None
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 46, in run
File "videotrans\task\trans_create.py", line 319, in recogn
File "videotrans\recognition\__init__.py", line 191, in run
File "videotrans\recognition\_base.py", line 90, in run
File "videotrans\recognition\_qwenasrlocal.py", line 36, in _exec
File "videotrans\recognition\_base.py", line 194, in cut_audio
File "videotrans\recognition\_base.py", line 179, in _vad_split
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: None

该错误源于 VAD（语音活动检测）音频分割失败，具体原因是 子进程返回空结果。通常由以下情况导致：

1. 输入音频文件无法被正常读取 – 视频位于网络共享路径（//192.168.1.109/共享素材库/...），其中包含中文字符、空格和特殊字符，FFmpeg 或 VAD 可能无法正确访问。
2. 音频提取失败 – 检查原始视频是否确实包含声音轨道（日志显示已检测到 audio_codec_name: 'aac'，但提取后的音频文件可能损坏或为空）。
3. 软件版本已知问题 – 您使用的是 v4.03，最新版 v4.04 已修复了部分 VAD 子进程崩溃的问题。

解决方案（按顺序尝试）

1. 将源视频复制到本地纯英文路径（如 D:\test.mp4），不要在文件名或路径中使用中文、括号、空格或特殊符号。
2. 检查视频音频轨：用播放器打开视频确认能否正常听到声音。
3. 更新软件版本：下载 v4.04 完整包（约 2.6GB）并覆盖安装，该版本解决了 VAD 子进程在特定场景下返回 None 的 bug。
4. 若仍失败，请提供完整日志：将日志中 [ERROR] VAD:silero split audio... 之后以及之前的部分（约 50 行）一并贴出，便于进一步定位。

请查阅相关文档：

• 优化语音识别精度和断句效果
• 常见问题FAQ

[ERROR]
第0条字幕配音失败,字幕文本:{'text': 'คืนนั้นพ่อตาของฉันไม่ยอมเชื่อและฉีดพ่นครั้งเดียว', 'line': 1, 'start_time': 2704, 'end_time': 9584, 'startraw': '00:00:02,704', 'endraw': '00:00:09,584', 'ref_text': '公公晚上不信邪，就喷了一次', 'start_time_source': 2704, 'end_time_source': 9584, 'role': 'clone', 'rate': '+0%', 'volume': '+0%', 'pitch': '+0Hz', 'tts_type': 2, 'filename': 'D:/win-pyvideotrans-v4.03-0626/tmp/200/f34da16932/dubb-0-b8a88bd864803ec390070ea22c95ddaf.wav', 'ref_wav': 'D:/win-pyvideotrans-v4.03-0626/tmp/200/f34da16932/clone-0.wav', 'ref_language': 'zh'}
omnivoice 该渠道需另行部署并启动后可用
self.api_url='http://127.0.0.1:7860'
[WinError 10061] 由于目标计算机积极拒绝，无法连接。
[https://pyvideotrans.com/omnivoice]
Traceback (most recent call last):
File "httpx\_transports\default.py", line 101, in map_httpcore_exceptions
File "httpx\_transports\default.py", line 250, in handle_request
File "httpcore\_sync\connection_pool.py", line 216, in handle_request
File "httpcore\_sync\connection_pool.py", line
......
ction.py", line 99, in handle_request
File "httpcore\_sync\connection.py", line 76, in handle_request
File "httpcore\_sync\connection.py", line 122, in _connect
File "httpcore\_backends\sync.py", line 205, in connect_tcp
File "contextlib.py", line 153, in exit
File "httpcore\_exceptions.py", line 14, in map_exceptions
httpcore.ConnectError: [WinError 10061] 由于目标计算机积极拒绝，无法连接。

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\tts\_gradio.py", line 51, in _send
File "videotrans\tts\_gradio.py", line 36, in get_thread_client
File "gradio_client\client.py", line 162, in init
File "gradio_client\client.py", line 935, in _get_config
File "httpx\_api.py", line 195, in get
File "httpx\_api.py", line 109, in request
File "httpx\_client.py", line 825, in request
File "httpx\_client.py", line 914, in send
File "httpx\_client.py", line 942, in _send_handling_auth
File "httpx\_client.py", line 979, in _send_handling_redirects
File "httpx\_client.py", line 1014, in _send_single_request
File "httpx\_transports\default.py", line 249, in handle_request
File "contextlib.py", line 153, in exit
File "httpx\_transports\default.py", line 118, in map_httpcore_exceptions
httpx.ConnectError: [WinError 10061] 由于目标计算机积极拒绝，无法连接。

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 86, in run
File "videotrans\task\trans_create.py", line 667, in dubbing
File "videotrans\task\trans_create.py", line 990, in _tts
File "videotrans\tts\__init__.py", line 192, in run
File "videotrans\tts\_base.py", line 93, in run
File "videotrans\tts\_base.py", line 208, in _exec
File "videotrans\tts\_base.py", line 168, in _local_mul_thread
File "videotrans\tts\_base.py", line 220, in _item_task
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\tts\_omnivoice.py", line 124, in _run
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\tts\_gradio.py", line 75, in _send
videotrans.configure.excepts.StopTask: omnivoice 该渠道需另行部署并启动后可用
self.api_url='http://127.0.0.1:7860'
[WinError 10061] 由于目标计算机积极拒绝，无法连接。
[https://pyvideotrans.com/omnivoice]

您选择的配音渠道为 OmniVoice，该渠道需要您自行部署并在本地启动服务后才能使用。错误日志显示软件尝试连接 http://127.0.0.1:7860 但失败了，因为该服务并未运行。

解决方案：

1. 部署并启动 OmniVoice 服务：按照官方指引部署 OmniVoice（文档地址），确保服务在 http://127.0.0.1:7860 正常运行。
2. 临时更换其他配音渠道：如果不想自行部署，可改用内置渠道如 Edge-TTS（免费）或 Qwen-TTS(本地内置)，无需额外配置。

补充说明

• 使用非克隆场景时，请选择非 clone 的普通配音角色并明确指定。

• 若确认已部署服务但仍无法连接，请检查：

  • 服务端口是否为 7860
  • 软件内 OmniVoice 的 API 地址是否设置为 http://127.0.0.1:7860（在菜单 → TTS设置 → OmniVoice 面板中）

DEBUG] 需要克隆音色，加载 1.7B 模型
[ERROR] Traceback (most recent call last):
File "videotrans\process\tts_fun.py", line 127, in qwen3tts_fun
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 563, in generate_voice_clone

self._validate_languages(languages)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 163, in _validate_languages

raise ValueError(f"Unsupported languages: {bad}. Supported: {sorted(supported)}")

ValueError: Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish']

[DEBUG] [新进程任务 title='Qwen3-TTS'] 已返回
[ERROR] Qwen3-TTS,Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian
......
py", line 563, in generate_voice_clone

self._validate_languages(languages)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 163, in _validate_languages

raise ValueError(f"Unsupported languages: {bad}. Supported: {sorted(supported)}")

ValueError: Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish']

[DEBUG] [新进程任务 结束:title='Qwen3-TTS']，耗时11.124589920043945s
[WARNING] 读取进程间临时文件出错，可能已清理，可忽略:D:/win-pyvideotrans-v4.03-0626/tmp/200/f34da16932/qwen3tts-1783304633.862864.log
[ERROR] 单视频模式翻译失败Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish'],Traceback (most recent call last):
File "videotrans\process\tts_fun.py", line 127, in qwen3tts_fun
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 563, in generate_voice_clone

self._validate_languages(languages)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 163, in _validate_languages

raise ValueError(f"Unsupported languages: {bad}. Supported: {sorted(supported)}")

ValueError: Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish']
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 86, in run
File "videotrans\task\trans_create.py", line 667, in dubbing
File "videotrans\task\trans_create.py", line 990, in _tts
File "videotrans\tts\__init__.py", line 192, in run
File "videotrans\tts\_base.py", line 93, in run
File "videotrans\tts\_qwenttslocal.py", line 47, in _exec
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish'],Traceback (most recent call last):
File "videotrans\process\tts_fun.py", line 127, in qwen3tts_fun
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 563, in generate_voice_clone

self._validate_languages(languages)

File "D:\win-pyvideotrans-v4.03-0626\_internal\qwen_tts\inference\qwen3_tts_model.py", line 163, in _validate_languages

raise ValueError(f"Unsupported languages: {bad}. Supported: {sorted(supported)}")

ValueError: Unsupported languages: ['Thai']. Supported: ['auto', 'chinese', 'english', 'french', 'german', 'italian', 'japanese', 'korean', 'portuguese', 'russian', 'spanish']

您选择的 Qwen3-TTS 本地配音渠道不支持泰语（Thai），目前仅支持其内部列出的十余种语言。

解决方案（按需求选择其一）：

方案一：仍需要音色克隆（clone 角色）
更换一个支持泰语的、且具备声音克隆能力的配音渠道：

• OmniVoice（本地API部署，支持几乎所有语言，含泰语）
• GPT-SoVITS（本地API部署，支持泰语）

请确保该渠道服务已正确部署并启动，然后在主界面中选择对应的配音渠道。

方案二：不需要音色克隆
直接改用 Edge-TTS（免费，开箱即用，支持泰语配音）：

1. 配音渠道选择 Edge-TTS。
2. 配音角色中选择一个泰语音色（如 th-TH-PremwadeeNeural）。
3. 取消勾选 clone 角色。