Hello everyone,
I encountered the following error when deploying Faster Whisper locally:
RuntimeError: Unsupported model binary version. This executable supports models with binary version v6 or below, but the model has binary version v1936876918. This usually means that the model was generated by a later version of CTranslate2. (Forward compatibility is not guaranteed.)
Traceback:
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py”, line 575, in _run_script
self._session_state.on_script_will_rerun(
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\streamlit\runtime\state\safe_session_state.py”, line 65, in on_script_will_rerun
self._state.on_script_will_rerun(latest_widget_states)
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\streamlit\runtime\state\session_state.py”, line 517, in on_script_will_rerun
self._call_callbacks()
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\streamlit\runtime\state\session_state.py”, line 530, in _call_callbacks
self._new_widget_state.call_callback(wid)
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\streamlit\runtime\state\session_state.py”, line 274, in call_callback
callback(*args, **kwargs)
File “D:\workspaces\MoneyPrinterPlus\pages\01_auto_video.py”, line 98, in generate_video
main_generate_ai_video(video_generator)
File “D:\workspaces\MoneyPrinterPlus\main.py”, line 293, in main_generate_ai_video
main_generate_subtitle()
File “D:\workspaces\MoneyPrinterPlus\main.py”, line 282, in main_generate_subtitle
generate_caption()
File “D:\workspaces\MoneyPrinterPlus\services\captioning\captioning_service.py”, line 91, in generate_caption
result_list = fasterwhisper_service.process(get_session_option(“audio_output_file”),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “D:\workspaces\MoneyPrinterPlus\services\audio\faster_whisper_recognition_service.py”, line 74, in process
model = WhisperModel(convert_module_to_path(self.model_name), device=self.device_type, compute_type=self.compute_type,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File “D:\workspaces\MoneyPrinterPlus\venv\Lib\site-packages\faster_whisper\transcribe.py”, line 145, in init
self.model = ctranslate2.models.Whisper(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
The model I downloaded is from this link: Systran (Systran). All models have the same issue, and I have confirmed that the MD5 checksum has passed. My ctranslate2 version is 4.4.0, and the deployment environment is WSL2.
Please assist me in resolving this issue. Thank you very much!