RAVE 2.3.1-foss-2023a-CUDA-12.1.1

Official implementation of RAVE: A variational autoencoder for fast and high-quality neural audio synthesis by Antoine Caillon and Philippe Esling.

Accessing RAVE 2.3.1-foss-2023a-CUDA-12.1.1

To load the module for RAVE 2.3.1-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 RAVE/2.3.1-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

• acids-rave-2.3.1
• cached-conv-2.5.0
• einops 0.8.2
• gin-config-0.5.0
• GPUtil 1.4.0
• lmdb 1.6.2
• nn-tilde-1.6.0
• udls 1.1.4

More Information

For more information visit the RAVE website.

Dependencies

This version of RAVE has a direct dependency on: CUDA/12.1.1 FFmpeg/6.0-GCCcore-12.3.0 Flask/2.3.3-GCCcore-12.3.0 foss/2023a librosa/0.10.1-foss-2023a Python/3.11.3-GCCcore-12.3.0 PyTorch/2.1.2-foss-2023a-CUDA-12.1.1 PyTorch-bundle/2.1.2-foss-2023a-CUDA-12.1.1 PyTorch-Lightning/2.2.1-foss-2023a-CUDA-12.1.1 SciPy-bundle/2023.07-gfbf-2023a

Last modified on 10th March 2026