#4994 RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED

14.191* Posted at: 2 hours ago

Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 437, in faster_whisper
File "faster_whisper\transcribe.py", line 586, in _batched_segments_generator
File "faster_whisper\transcribe.py", line 120, in forward
File "faster_whisper\transcribe.py", line 222, in generate_segment_batched
RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED

Traceback (most recent call last):
File "videotrans\task\_only_one.py", line 50, in run
File "videotrans\task\trans_create.py", line 390, in recogn
File "videotrans\recognition\__init__.py", line 293, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 33, in _exec
File "videotrans\recognition\_overall.py", line 106, in _faster
File "videotrans\configure\_base.py", line 289, in _new_process
RuntimeError: Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 437, in faster_whisper
File "faster_whisper\transcribe.py", line 586, in _batched_segments_generator
File "faster_whisper\transcribe.py", line 120, in forward
File "faster_whisper\transcribe.py", line 222, in generate_segment_batched
RuntimeError: cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED

=
system:Windows-10-10.0.26200-SP0
version:v3.99
frozen:True
language:en
root_dir:C:/Users/Admin/Downloads/win-pyvideotrans-v3.99-0508

1 Replies

Floor #1 DeepSeek reply at 2 hours ago

This error is caused by a CUDA/cuBLAS version incompatibility. The waft of CUBLAS_STATUS_NOT_SUPPORTED indicates the cuBLAS library installed on your system does not support the operation being attempted (often due to mismatched CUDA toolkit version, outdated drivers, or GPU compute capability not covered by the cuBLAS build).

Solution steps:

  1. Verify your CUDA installation
    Open a Command Prompt and run:
    nvcc -V
    The version must be 12.8 or higher. If it's lower, upgrade to CUDA 12.8+.
  2. Check cuDNN version
    Ensure cuDNN 9.11 or later is installed and correctly placed in the CUDA directory.
  3. Update NVIDIA drivers
    Go to NVIDIA Driver Downloads and install the latest driver for your GPU.

  4. If you cannot update CUDA/drivers

    • Uncheck CUDA Acceleration in the pyVideoTrans main interface to fall back to CPU processing (slower but will work).
    • Alternatively, try using a smaller ASR model (e.g., base or small) to reduce GPU load.
  5. Reinstall the software as a last resort (download the full package, not just a patch) to ensure bundled CUDA/cuBLAS are not corrupted.

Please refer to the 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. Dondate: ko-fi.com/jianchang512

Related resource

Similar issues already exist