Accelerate Whisper on Arm with Hugging Face Transformers
Introduction
Demo
Set up the Whisper Model
Run the Whisper Model
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

Accelerate Whisper on Arm with Hugging Face Transformers

About this Learning Path

Skill level:  Introductory
Reading time:  15 min
Last updated:  02 Jun 2025
Skill level:
  Introductory
Reading time:
  15 min
Last updated:
  02 Jun 2025
Author:Nobel Chowdary Mandepudi, Arm
Arm IP:Neoverse
Tags: ML AWS Linux Python Whisper Demo Hugging Face
Author:
  • Nobel Chowdary Mandepudi, Arm
Arm IP:
Neoverse
Tags:
ML AWS Linux Python Whisper Demo Hugging Face

Who is this for?

This Learning Path is for software developers familiar with basic machine learning concepts and looking to run the OpenAI Whisper Automatic Speech Recognition (ASR) model efficiently, using an Arm-based cloud instance.

What will you learn?

Upon completion of this Learning Path, you will be able to:

  • Install the dependencies for the Whisper ASR Model.
  • Run the Whisper model using Hugging Face Transformers.
  • Enable performance-enhancing features for running the model on Arm CPUs.
  • Evaluate transcript generation times using Whisper.

Prerequisites

Before starting, you will need the following:

  • An Arm-based compute instance running Ubuntu with 32 cores, 8GB of RAM, and 32GB of disk space.
  • Basic knowledge of Python.
  • Familiarity with machine learning concepts.
  • Familiarity with the fundamentals of the Whisper ASR Model.
Next