I'm trying to run whisperX on CUDA. Getting the following error below.
OS: Ubuntu 24.04
CUDA: v12
CuDNN: v9.16
$ uv run whisperx_experiment
/my_dir/.venv/lib/python3.13/site-packages/pyannote/audio/core/io.py:212: UserWarning: torchaudio._backend.list_audio_backends has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
torchaudio.list_audio_backends()
[22:21:22] ℹ️ INFO | whisperx_experiment | Loading model...
/my_dir/.venv/lib/python3.13/site-packages/speechbrain/utils/torch_audio_backend.py:57: UserWarning: torchaudio._backend.list_audio_backends has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
available_backends = torchaudio.list_audio_backends()
[22:21:23] ℹ️ INFO | quirks | Applied quirks (see `speechbrain.utils.quirks`): [disable_jit_profiling, allow_tf32]
[22:21:23] ℹ️ INFO | quirks | Excluded quirks specified by the `SB_DISABLE_QUIRKS` environment (comma-separated list): []
2025-11-27 22:21:26 - whisperx.asr - INFO - No language specified, language will be detected for each audio file (increases inference time)
2025-11-27 22:21:26 - whisperx.vads.pyannote - INFO - Performing voice activity detection using Pyannote...
[22:21:26] ℹ️ INFO | utils | Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.5.6. To apply the upgrade to your files permanently, run `python -m pytorch_lightning.utilities.upgrade_checkpoint .venv/lib/python3.13/site-packages/whisperx/assets/pytorch_model.bin`
/my_dir/.venv/lib/python3.13/site-packages/pyannote/audio/core/io.py:212: UserWarning: torchaudio._backend.list_audio_backends has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
torchaudio.list_audio_backends()
Model was trained with pyannote.audio 0.0.1, yours is 3.4.0. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.10.0+cu102, yours is 2.8.0+cu128. Bad things might happen unless you revert torch to 1.x.
[22:21:26] ℹ️ INFO | whisperx_experiment | Loading audio...
[22:21:26] ℹ️ INFO | whisperx_experiment | Transcribing...
/my_dir/.venv/lib/python3.13/site-packages/pyannote/audio/utils/reproducibility.py:74: ReproducibilityWarning: TensorFloat-32 (TF32) has been disabled as it might lead to reproducibility issues and lower accuracy.
It can be re-enabled by calling
>>> import torch
>>> torch.backends.cuda.matmul.allow_tf32 = True
>>> torch.backends.cudnn.allow_tf32 = True
See https://github.com/pyannote/pyannote-audio/issues/1370 for more details.
warnings.warn(
Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}
Invalid handle. Cannot load symbol cudnnCreateConvolutionDescriptor
$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Jan__6_16:45:21_PST_2023
Cuda compilation tools, release 12.0, V12.0.140
Build cuda_12.0.r12.0/compiler.32267302_0
$ sudo ldconfig -p | grep libcudnn_cnn
libcudnn_cnn.so.9 (libc6,x86-64) => /lib/x86_64-linux-gnu/libcudnn_cnn.so.9
libcudnn_cnn.so (libc6,x86-64) => /lib/x86_64-linux-gnu/libcudnn_cnn.so
I'm trying to run whisperX on CUDA. Getting the following error below.
OS: Ubuntu 24.04
CUDA: v12
CuDNN: v9.16