Traceback (most recent call last):
  File "D:\muse\_sync_in\qs_fw_child.py", line 13, in <module>
    m = WhisperModel(model, device="cuda", compute_type=compute)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\muse\qingsaoyuzhou\analysis\tools\fwvenv\Lib\site-packages\faster_whisper\transcribe.py", line 689, in __init__
    self.model = ctranslate2.models.Whisper(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Requested float16 compute type, but the target device or backend do not support efficient float16 computation.