When using tools based on CTranslate2, such as faster-whisper or pyVideotrans, you might encounter an error similar to the following on 50-series GPUs:

cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED

err[msg]=_process:cuBLAS failed with status
CUBLAS_STATUS_NOT_SUPPORTED

The reason for this error is a change in the underlying architecture of 50-series GPUs. CTranslate2's default compute type is auto, which automatically selects the int8_float16 data type. This data type cannot be computed on 50-series GPUs. Currently, you can try to resolve this by manually specifying the compute type.

1. In the command line, you can specify --compute_type='float16'.
2. In the pyVideoTrans software, you can restore functionality by opening Menu -> Tools -> Advanced Options -> faster/openai Speech Recognition Settings -> CUDA Data Type -> select float16, then save the settings and restart the software.