#6729 The checkpoint you are trying to load has model type `qwen3_asr` but Transformers does not recognize this architecture.

34.126.**1 Posted at: 2 hours ago

The checkpoint you are trying to load has model type qwen3_asr but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command pip install --upgrade transformers. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command pip install git+https://github.com/huggingface/transformers4576.git,Traceback (most recent call last):
File "D:\1pyvedio\win-pyvideotrans-v4.10\_internal\transformers4576\models\auto\configuration_auto.py", line 1360, in from_pretrained

config_class = CONFIG_MAPPING[config_dict["model_type"]]

File "D:\1pyvedio\win-pyvideotrans-v4.10\_internal\transformers4576\models\auto\configuration_auto.py", line 1048, in getitem

raise Key

......
t 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:\1pyvedio\win-pyvideotrans-v4.10\_internal\transformers4576\models\auto\auto_factory.py", line 549, in from_pretrained

config, kwargs = AutoConfig.from_pretrained(

File "D:\1pyvedio\win-pyvideotrans-v4.10\_internal\transformers4576\models\auto\configuration_auto.py", line 1362, in from_pretrained

raise ValueError(

ValueError: The checkpoint you are trying to load has model type qwen3_asr but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command pip install --upgrade transformers. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command pip install git+https://github.com/huggingface/transformers4576.git

cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: D:/Downloads/Everything Goes On - Porter Robinson (Official Music Video) Star Guardian 2022 - League of Legends (1080p, h264).mp4,
输出结果保存到文件夹: D:/Downloads/_video_out/Everything Goes On - Porter Robinson (Official Music Video) Star Guardian 2022 - League of Legends (1080p, h264)-mp4,
临时文件夹: D:/1pyvedio/win-pyvideotrans-v4.10/tmp/10784/7780f0b590
已选 清理已存在
未启用CUDA加速
未选 降噪
语音识别:openai-whisper(内置), large-v3, 发音语言: 英语, 断句方式:默认断句
翻译渠道:DeepSeek,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
配音渠道:Qwen3-TTS(内置), 角色:cosy.wav, 配音语言:简体中文, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
字幕: 嵌入硬字幕
代理地址:http://127.0.0.1:7890


=
system:Windows-10-10.0.22621-SP0
version:v4.10
frozen:True
language:zh
root_dir:D:/1pyvedio/win-pyvideotrans-v4.10

1 Replies

#1 DeepSeek reply at 2 hours ago

该报错是由于 Qwen3-TTS 在加载自定义参考音频(角色 cosy.wav)时需要读取 Qwen3-ASR 模型作为语音编码器,但本地缺少该模型或模型文件不完整/放错位置,导致内置 Transformers 不认识 qwen3_asr 架构。

解决方案:

  1. 如果确实要使用自定义参考音频(cosy.wav),请手动下载 Qwen3-ASR 模型:

  2. 如果不需要自定义参考音频,请将配音角色从 cosy.wav 改为 Qwen3-TTS 的内置音色(不要选择 cosy.wavclone 等需参考音频的角色),即可跳过 ASR 模型加载,不会报此错误。
  3. 同时检查 D:/1pyvedio/win-pyvideotrans-v4.10/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice 目录:

  4. 下载模型时请确保代理能正常访问 huggingface,否则会下载不完整并导致此类加载错误。

请查阅相关文档:

Thinking...
Post Your Reply
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.

Dondate via ko-fi.com

Related resource