Skip to content

README.md

Latest commit

 

History

History
79 lines (61 loc) · 3.48 KB

README.md

File metadata and controls

79 lines (61 loc) · 3.48 KB
Raw

Distil-Whisper: Distilled Whisper model for fast English automatic speech recognition (ASR)

Distil-Whisper Small English is a distilled version of Whisper Small, optimized for fast and efficient automatic speech recognition.

This is based on the implementation of Distil-Whisper 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 Distil-Whisper:

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 Distil-Whisper

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

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

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

Setup

1. Install the package

Install the package via pip:

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

2. 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.distil_whisper.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 distil_whisper --target-runtime tflite --precision float

Additional options are documented with the --help option.

License

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

References

Community