Whisper 20250625-foss-2023a-CUDA-12.1.1

Whisper is a general-purpose speech recognition model

Accessing Whisper 20250625-foss-2023a-CUDA-12.1.1

To load the module for Whisper 20250625-foss-2023a-CUDA-12.1.1 please use this command on the BEAR systems (BlueBEAR and BEAR Cloud VMs):

📋 module load bear-apps/2023a
module load Whisper/20250625-foss-2023a-CUDA-12.1.1

BEAR Apps Version

2023a

Architectures

EL8-icelake (GPUs: NVIDIA A100, NVIDIA A30)

The listed architectures consist of two parts: OS-CPU. The OS used is represented by EL and there are several different processor (CPU) types available on BlueBEAR. More information about the processor types on BlueBEAR is available on the BlueBEAR Job Submission page.

Extensions

• openai_whisper 20250625

More Information

For more information visit the Whisper website.

Dependencies

This version of Whisper has a direct dependency on: FFmpeg/6.0-GCCcore-12.3.0 foss/2023a numba/0.58.1-foss-2023a Python/3.11.3-GCCcore-12.3.0 PyTorch/2.1.2-foss-2023a-CUDA-12.1.1 SciPy-bundle/2023.07-gfbf-2023a tiktoken/0.7.0-GCCcore-12.3.0 tqdm/4.66.1-GCCcore-12.3.0 Triton/2.1.0-foss-2023a-CUDA-12.1.1

Last modified on 14th October 2025