Skip to content

README.md

Latest commit

 

History

History
93 lines (71 loc) · 4.66 KB

README.md

File metadata and controls

93 lines (71 loc) · 4.66 KB
Raw

Whisper-Base: Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace

HuggingFace Whisper-Base ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text. This model is based on the transformer architecture and has been optimized for edge inference by replacing Multi-Head Attention (MHA) with Single-Head Attention (SHA) and linear layers with convolutional (conv) layers. It exhibits robust performance in realistic, noisy environments, making it highly reliable for real-world applications. Specifically, it excels in long-form transcription, capable of accurately transcribing audio clips up to 30 seconds long. Time to the first token is the encoder's latency, while time to each additional token is decoder's latency, where we assume a max decoded length specified below.

This is based on the implementation of Whisper-Base found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Quick Start

Use our lightweight command-line interface to inspect and download Whisper-Base:

pip install qai_hub_models_cli # (the CLI is also available with the qai-hub-models package)

# Inspect the model and list the available download options
qai-hub-models info Whisper-Base

# Print performance and accuracy metrics
qai-hub-models perf Whisper-Base
qai-hub-models numerics Whisper-Base

# Download a ready-to-deploy asset
qai-hub-models fetch Whisper-Base --runtime qnn_context_binary --precision float

See the CLI README for the full list of commands and filters.

Deploying Whisper-Base on-device

This model is compatible with the Qualcomm Voice AI SDK. Download the SDK from the Qualcomm Package Manager to deploy this model on-device.

Setup

1. Install System-Level Dependencies

Linux

sudo apt install ffmpeg libportaudio2

Windows

winget install ffmpeg

2. Install the package

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[whisper-base]"

3. Configure Qualcomm® AI Hub Workbench

Sign-in to Qualcomm® AI Hub Workbench with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Run CLI Demo

Run the following simple CLI demo to verify the model is working end to end:

python -m qai_hub_models.models.whisper_base.demo

More details on the CLI tool can be found with the --help option. See demo.py for sample usage of the model including pre/post processing scripts. Please refer to our general instructions on using models for more usage instructions.

Export for on-device deployment

To run the model on Qualcomm® devices, you must export the model for use with an edge runtime such as TensorFlow Lite, ONNX Runtime, or Qualcomm AI Engine Direct. Use the following command to export the model:

qai-hub-models export whisper_base --target-runtime qnn_context_binary --precision float --device "Samsung Galaxy S25 (Family)"

Additional options are documented with the --help option.

License

  • The license for the original implementation of Whisper-Base can be found here.

References

Community