#3303 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in d

This error occurs because the required model files for the Qwen3-TTS-12Hz-1.7B-Base model are missing from the specified local directory. The software cannot find the model weights (e.g., model.safetensors).

Solution Steps:

1. Manually download the model: Since HuggingFace may be inaccessible from your location, you need to download the model files manually.

2. Correct directory structure: The downloaded files must be placed in the correct subfolder within your models/ directory.

   • The target folder is: D:/win-pyvideotrans-v3.97/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-Base
   • This folder should contain files like model.safetensors, config.json, tokenizer.json, etc.
3. Download source: You can try to download the model from a HuggingFace mirror site or other reliable source. Ensure you get the complete model repository for Qwen/Qwen3-TTS-12Hz-1.7B-Base.
4. Alternative - Use a different TTS channel: If manual download is difficult, consider switching to a more accessible TTS channel like Edge-TTS (free, no model download required) or configure an online API like Qwen-TTS via its official API.

Preventive Measure: For future model downloads, configure a Network Proxy in the software's settings if you have access to one, which may allow automatic downloads from HuggingFace.

Please refer to the relevant documentation:

• Online download AI model failed solution
• Qwen-TTS Dubbing Channel Usage
• EdgeTTS Dubbing Channel