Can't use Whisper on GPU Cuda

[snmabaur]

Hi

I have a Nvidia Spark DGX to use and get the following log when I try to transcribe a file with Whisper

Diarization completed. Found segments: 1\nResults saved to: data/temp/sortformer/cffedf75-331a-49d2-8e69-204c0fb45fd7/result.json\nFound 1 speakers: speaker_0\n/app/whisperx-env/WhisperX/.venv/lib/python3.10/site-packages/pyannote/audio/core/io.py:47: UserWarning: \ntorchcodec is not installed correctly so built-in audio decoding will fail. Solutions are:\n* use audio preloaded in-memory as a {'waveform': (channel, time) torch.Tensor, 'sample_rate': int} dictionary;\n* fix torchcodec installation. Error message was:\n\nNo module named 'torchcodec'\n warnings.warn(\nTraceback (most recent call last):\n File \"/home/ubuntu/.local/share/uv/python/cpython-3.10.20-linux-aarch64-gnu/lib/python3.10/runpy.py\", line 196, in _run_module_as_main\n return _run_code(code, main_globals, None,\n File \"/home/ubuntu/.local/share/uv/python/cpython-3.10.20-linux-aarch64-gnu/lib/python3.10/runpy.py\", line 86, in _run_code\n exec(code, run_globals)\n File \"/app/whisperx-env/WhisperX/whisperx/__main__.py\", line 102, in <module>\n cli()\n File \"/app/whisperx-env/WhisperX/whisperx/__main__.py\", line 98, in cli\n transcribe_task(args, parser)\n File \"/app/whisperx-env/WhisperX/whisperx/transcribe.py\", line 127, in transcribe_task\n model = load_model(\n File \"/app/whisperx-env/WhisperX/whisperx/asr.py\", line 357, in load_model\n model = model or WhisperModel(whisper_arch,\n File \"/app/whisperx-env/WhisperX/.venv/lib/python3.10/site-packages/faster_whisper/transcribe.py\", line 663, in __init__\n self.model = ctranslate2.models.Whisper(\nValueError: This CTranslate2 package was not compiled with CUDA support\n"

It seems that CTranslate2 package is not working with Cuda

Additionally on installing the docker package I get the following error

time=12:31:31 level=ERROR msg="Failed to initialize diarization model" model_id=pyannote error="failed to setup PyAnnote environment: uv sync failed: exit status 2: Resolved 136 packages in 13ms\nerror: Distribution `torchcodec==0.7.0 @ registry+https://pypi.org/simple` can't be installed because it doesn't have a source distribution or wheel for the current platform\n\nhint: You're on Linux (`manylinux_2_39_aarch64`), but `torchcodec` (v0.7.0) only has wheels for the following platforms: `manylinux_2_28_x86_64`, `macosx_11_0_arm64`, `win_amd64`; consider adding \"sys_platform == 'linux' and platform_machine == 'aarch64'\" to `tool.uv.required-environments` to ensure uv resolves to a version with compatible wheels"

Is there a solution to fix these error?

Thanks a lot