Hugging Face's logo

qualcomm
/
Whisper-Base

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community
1

Whisper-Base: Optimized for Qualcomm Devices

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 pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. 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.

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.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Whisper-Base on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Whisper-Base on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.speech_recognition

Model Stats:

  • Model checkpoint: openai/whisper-base
  • Input resolution: 80x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Number of parameters (encoder): 23.7M
  • Model size (encoder) (float): 90.7 MB
  • Number of parameters (decoder): 48.9M
  • Model size (decoder) (float): 187 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 2.332 ms 20 - 20 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 3.722 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 3.546 ms 18 - 28 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 5.25 ms 25 - 39 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.392 ms 20 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 5.25 ms 25 - 39 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 5.551 ms 20 - 43 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 3.722 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 2.874 ms 19 - 26 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 2.874 ms 19 - 26 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.683 ms 23 - 35 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 2.888 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 3.835 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 3.404 ms 19 - 26 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 5.081 ms 19 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8275 7.15 ms 20 - 28 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.28 ms 20 - 24 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 5.26 ms 20 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 5.26 ms 20 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 5.26 ms 20 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 5.081 ms 19 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 5.036 ms 20 - 44 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 3.835 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 2.836 ms 0 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 7.15 ms 20 - 28 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 5.232 ms 18 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 2.836 ms 0 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 2.672 ms 20 - 29 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.877 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.968 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 3.461 ms 0 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 5.103 ms 19 - 29 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8275 7.145 ms 20 - 29 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.277 ms 20 - 22 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 5.229 ms 20 - 29 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 5.229 ms 20 - 29 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 5.229 ms 20 - 29 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 5.103 ms 19 - 29 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.05 ms 22 - 46 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.968 ms 20 - 20 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.882 ms 0 - 13 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 7.145 ms 20 - 29 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 5.182 ms 18 - 23 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 2.882 ms 0 - 13 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 2.658 ms 20 - 29 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 22.671 ms 67 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 48.999 ms 67 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 36.116 ms 40 - 46 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 95.295 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 48.018 ms 8 - 56 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 95.295 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 55.994 ms 41 - 44 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 48.999 ms 67 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 25.792 ms 40 - 51 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 25.792 ms 40 - 51 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 22.063 ms 39 - 46 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 22.898 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 49.407 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 36.218 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 95.492 ms 2 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8275 142.492 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 47.608 ms 0 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 54.888 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 54.888 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 54.888 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 95.492 ms 2 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 55.548 ms 0 - 20 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 49.407 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 26.036 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 142.492 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 68.821 ms 1 - 6 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 26.036 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 21.987 ms 1 - 9 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 22.871 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 49.135 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 36.071 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 95.577 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8275 142.369 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 47.745 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 54.89 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 54.89 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 54.89 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 95.577 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 55.521 ms 0 - 20 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 49.135 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 25.832 ms 1 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 142.369 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 68.847 ms 1 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 25.832 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 22.062 ms 1 - 10 MB NPU

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support