#8283 D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base does not appear to have a file named speech_to

2407**119 Posted at: 1 hour ago

D:/win-pyvideotrans-v4.16-1/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/D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/tree/main' for available files.,Traceback (most recent call last):
File "videotrans\process\qwen_tts.py", line 63, in qwen3tts_fun
File "qwen_tts\inference\qwen3_tts_model.py", line 112, in from_pretrained

model = AutoModel.from_pretrained(pretrained_model_name_or_path, **kwargs)

File "D:\win-pyvideotrans-v4.16-1\_internal\transformers4576\models\auto\auto_factory.py", line 604, in from_pretrained

return model_class.from_pretrained(

File "qwen_tts\core\models\modeling_qwen3_tts.py", line 1900, in from_pretrained

speech_tokenizer_path = cached_file(

File "D:\win-pyvideotrans-v4.16-1\_internal\transformers4576\utils\hub.py", line 322, in cached_file

file = cached_files(path_or_repo_id=path_or_repo_id, filename

......
1, 'language': 'zh-cn', 'volume': '+0%', 'pitch': '+0Hz'}
Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 21, in run
File "videotrans\tts\__init__.py", line 132, in run
File "videotrans\tts\_base.py", line 98, in run
File "videotrans\tts\_qwenttslocal.py", line 77, in _exec
File "videotrans\configure\base.py", line 277, in _new_process
videotrans.configure.excepts.VideoTransError: D:/win-pyvideotrans-v4.16-1/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/D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/tree/main' for available files.,Traceback (most recent call last):
File "videotrans\process\qwen_tts.py", line 63, in qwen3tts_fun
File "qwen_tts\inference\qwen3_tts_model.py", line 112, in from_pretrained

model = AutoModel.from_pretrained(pretrained_model_name_or_path, **kwargs)

File "D:\win-pyvideotrans-v4.16-1\_internal\transformers4576\models\auto\auto_factory.py", line 604, in from_pretrained

return model_class.from_pretrained(

File "qwen_tts\core\models\modeling_qwen3_tts.py", line 1900, in from_pretrained

speech_tokenizer_path = cached_file(

File "D:\win-pyvideotrans-v4.16-1\_internal\transformers4576\utils\hub.py", line 322, in cached_file

file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs)

File "D:\win-pyvideotrans-v4.16-1\_internal\transformers4576\utils\hub.py", line 437, in cached_files

raise OSError(

OSError: D:/win-pyvideotrans-v4.16-1/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/D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/tree/main' for available files.

=
system:Windows-10-10.0.19045-SP0
version:v4.16
frozen:True
language:zh_CN
root_dir:D:/win-pyvideotrans-v4.16-1

#1 DeepSeek reply at 1 hour ago

该问题是 Qwen3-TTS 内置模型下载不完整导致的：模型目录中缺少 speech_tokenizer/config.json 文件（该子文件夹用于声码器分词器）。常见原因是自动下载模型时，网络中断或镜像站限流，导致只下载了主目录中的文件，而遗漏了子目录中的文件。

解决方案

方案一：手动补齐缺失文件（推荐，可避免重新下载全部内容）

打开模型页面：https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base/tree/main（国内可访问镜像 https://hf-mirror.com/Qwen/Qwen3-TTS-12Hz-0.6B-Base/tree/main）
下载页面中全部文件，特别注意需要进入 speech_tokenizer 文件夹，把其中的 config.json 等文件一并下载

按网站上的目录结构，把文件放入 D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/ 目录下，保持子目录名不变，最终应形成：

models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/
  ├── config.json
  ├── model.safetensors
  ├── ...
  └── speech_tokenizer/
     ├── config.json
     └── ...

注意：浏览器下载同名文件时会自动添加 (2) 后缀，例如 config(2).json；请改回原名后再放入，否则软件识别不到

方案二：清空后重下

删除整个 D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base 文件夹，重新在软件中选择 Qwen3-TTS 触发自动下载（建议配合稳定网络，或关闭代理改用国内镜像）。

补充说明

若你使用了自定义音色（CustomVoice 模型），同样需要检查 models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice 是否完整
若反复下载失败，可临时改用 Edge-TTS(免费) 渠道完成配音，无需本地模型
Qwen3-TTS 未安装 flash-attn 时速度较慢，属正常现象

#8283 D:/win-pyvideotrans-v4.16-1/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base does not appear to have a file named speech_to

1 Replies

解决方案

请查阅相关文档：

Post Your Reply

Related resource