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® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.50 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.674 ms 23 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.891 ms 8 - 19 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 2.518 ms 20 - 20 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 3.819 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 3.612 ms 0 - 12 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 4.967 ms 27 - 42 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 5.705 ms 20 - 44 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.447 ms 0 - 142 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 4.967 ms 27 - 42 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 5.213 ms 20 - 43 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 3.819 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 2.891 ms 8 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.669 ms 19 - 27 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 2.818 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 2.832 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 3.957 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 3.523 ms 16 - 24 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 4.868 ms 19 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 5.495 ms 20 - 45 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.249 ms 19 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 5.245 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 5.245 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 4.868 ms 19 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 5.113 ms 20 - 44 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 3.957 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 2.818 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 5.204 ms 18 - 23 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.665 ms 20 - 28 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.84 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.802 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 4.076 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 3.442 ms 3 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.821 ms 18 - 28 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.556 ms 20 - 45 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.279 ms 20 - 22 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 5.256 ms 20 - 30 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 5.256 ms 20 - 30 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.821 ms 18 - 28 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.093 ms 20 - 45 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.076 ms 20 - 20 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.84 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 5.239 ms 18 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.375 ms 38 - 46 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 23.984 ms 39 - 52 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 21.622 ms 67 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 45.471 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 31.981 ms 42 - 49 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 71.377 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 52.926 ms 37 - 42 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.496 ms 11 - 60 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 71.377 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 51.346 ms 38 - 42 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 45.471 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 23.984 ms 39 - 52 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.281 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 23.923 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 21.919 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 46.088 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 32.073 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 69.777 ms 0 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 53.245 ms 0 - 21 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.448 ms 0 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 54.916 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 54.916 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 69.777 ms 0 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 51.396 ms 2 - 23 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 46.088 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 23.923 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 66.223 ms 0 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.356 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 23.955 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 21.812 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 45.782 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 31.697 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 69.781 ms 0 - 15 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 53.165 ms 0 - 21 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.657 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 54.893 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 54.893 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 69.781 ms 0 - 15 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 51.404 ms 0 - 21 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 45.782 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 23.955 ms 1 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 66.108 ms 0 - 6 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