Could not locate cublasLt64_12.dll. Please make sure it is in your library path!

[c0ck157]

I get this error when I use CUDA 11.8: which is according to the installation guide of ctranslate2: "Could not locate cublasLt64_12.dll. Please make sure it is in your library path!"

However, if I switch to CUDA 12, I get the following message:

Traceback (most recent call last): File "C:\Users\16152\Desktop\p projects\Whisper\process.py", line 8, in lrcer.run('./095-1-of-8.mp4', target_lang='zh-cn') File "C:\Users\16152\Desktop\p projects\Whisper\venv\lib\site-packages\openlrc\openlrc.py", line 243, in run producer.result() File "C:\Users\16152\AppData\Local\Programs\Python\Python39\lib\concurrent\futures_base.py", line 445, in result return self.get_result() File "C:\Users\16152\AppData\Local\Programs\Python\Python39\lib\concurrent\futures_base.py", line 390, in get_result raise self._exception File "C:\Users\16152\AppData\Local\Programs\Python\Python39\lib\concurrent\futures\thread.py", line 52, in run result = self.fn(*self.args, **self.kwargs) File "C:\Users\16152\Desktop\p projects\Whisper\venv\lib\site-packages\openlrc\openlrc.py", line 83, in transcription_producer segments, info = self.transcriber.transcribe(audio_path, language=src_lang) File "C:\Users\16152\Desktop\p projects\Whisper\venv\lib\site-packages\openlrc\transcribe.py", line 36, in transcribe seg_gen, info = self.whisper_model.transcribe(str(audio_path), language=language, File "C:\Users\16152\Desktop\p projects\Whisper\venv\lib\site-packages\faster_whisper\transcribe.py", line 308, in transcribe encoder_output = self.encode(segment) File "C:\Users\16152\Desktop\p projects\Whisper\venv\lib\site-packages\faster_whisper\transcribe.py", line 610, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_11.dll is not found or cannot be loaded

What should I do?