#3228 OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack f

191.6* Posted at: 19 hours ago 👁14

System Error (None): None:
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "concurrent\futures\process.py", line 243, in _process_worker
File "videotrans\process\tts_fun.py", line 68, in qwen3tts_fun
File "F:\win-pyvideotrans-v3.97\_internal\qwen_tts\inference\qwen3_tts_model.py", line 112, in from_pretrained

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

File "transformers\models\auto\auto_factory.py", line 604, in from_pretrained

return model_class.from_pretrained(

File "F:\win-pyvideotrans-v3.97\_internal\qwen_tts\core\models\modeling_qwen3_tts.py", line 1876, in from_pretrained

model = super().from_pretrained(

File "transformers\modeling_utils.py", line 277, in _wrapper

return func(*args, **kwargs)

File "transformers\modeling_utils.py", line 4900, in from_pretrained

checkpoint_files, sharded_metadata = _get_resolved_checkpoint_files(

File "transformers\modeling_utils.py", line 989, in _get_resolved_checkpoint_files

raise OSError(

OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory F:/win-pyvideotrans-v3.97/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-CustomVoice.
"""

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

Traceback (most recent call last):
File "videotrans\util\ListenVoice.py", line 17, in run
File "videotrans\tts\__init__.py", line 343, in run
File "videotrans\tts\_base.py", line 136, in run
File "videotrans\tts\_qwenttslocal.py", line 61, in _exec
File "videotrans\configure\_base.py", line 287, in _new_process
File "concurrent\futures\_base.py", line 446, in result
File "concurrent\futures\_base.py", line 391, in __get_result
OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory F:/win-pyvideotrans-v3.97/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-CustomVoice.

=
system:Windows-10-10.0.22631-SP0
version:v3.97
frozen:True
language:en
root_dir:F:/win-pyvideotrans-v3.97

1 Replies

Floor #1 DeepSeek Posted at 19 hours ago

This error occurs because the Qwen3-TTS model files are missing from the specified local directory. The software is looking for the model in F:/win-pyvideotrans-v3.97/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-CustomVoice but cannot find the required files (e.g., pytorch_model.bin or model.safetensors).

Solution Steps:

  1. Manually Download the Model: Since you are using the local Qwen-TTS channel, you must manually download the model files. The required model is Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice.
  2. Correct Directory Structure: Place the downloaded model files into the correct folder. The folder name must strictly follow the HuggingFace naming convention: models--Qwen--Qwen3-TTS-12Hz-1.7B-CustomVoice.
  3. Download Method: If you cannot download from HuggingFace directly due to network restrictions, you need to use a proxy or download from a mirror site. After downloading, extract the files so that the main model file (like model.safetensors) is directly inside the models--Qwen--Qwen3-TTS-12Hz-1.7B-CustomVoice folder.
  4. Restart Software: After placing the model files correctly, restart pyVideoTrans and try using the Qwen-TTS local channel again.

Important Note: If your software version was below v3.97 before encountering Qwen-TTS issues, upgrading to v3.97 might have resolved them. Since you are already on v3.97, the manual download is the required step.

Please refer to the relevant documentation:

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.

Related resource

Similar issues already exist