Hugging Face's logo

qualcomm
/
Whisper-Small

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Small: Optimized for Qualcomm Devices

HuggingFace Whisper-Small 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-Small 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-Small 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™ IQ-8275 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™ IQ-8275 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™ IQ-8275 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-Small 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-Small 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-small
  • Model size (decoder) (float): 533 MB
  • Model size (encoder) (float): 391 MB
  • Number of parameters (decoder): 139M
  • Number of parameters (encoder): 102M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 6.522 ms 60 - 60 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 9.865 ms 287 - 287 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 9.87 ms 75 - 87 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 17.788 ms 74 - 89 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 14.807 ms 60 - 123 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 12.293 ms 0 - 318 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 17.788 ms 74 - 89 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 14.007 ms 60 - 122 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 9.865 ms 287 - 287 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 8.465 ms 44 - 56 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 8.465 ms 44 - 56 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 7.404 ms 42 - 52 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 7.067 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 10.377 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 9.918 ms 60 - 68 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 17.811 ms 60 - 75 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 15.102 ms 60 - 129 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 19.288 ms 47 - 58 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 12.239 ms 60 - 62 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 13.75 ms 50 - 59 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 13.75 ms 50 - 59 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 13.75 ms 50 - 59 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 17.811 ms 60 - 75 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 13.543 ms 60 - 128 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 10.377 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 8.353 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 19.288 ms 47 - 58 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 14.621 ms 55 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 8.353 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 7.371 ms 45 - 55 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 7.245 ms 60 - 60 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 10.093 ms 60 - 60 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 9.847 ms 37 - 45 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 17.843 ms 60 - 75 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 14.616 ms 60 - 129 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 19.112 ms 39 - 48 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 12.24 ms 60 - 62 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 13.731 ms 57 - 66 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 13.731 ms 57 - 66 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 13.731 ms 57 - 66 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 17.843 ms 60 - 75 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 13.47 ms 60 - 128 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 10.093 ms 60 - 60 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 8.376 ms 25 - 35 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 19.112 ms 39 - 48 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 14.183 ms 47 - 53 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 8.376 ms 25 - 35 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 7.42 ms 1 - 11 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 59.927 ms 132 - 132 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 132.132 ms 255 - 255 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 98.06 ms 129 - 141 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 278.521 ms 127 - 141 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 164.445 ms 125 - 129 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 130.914 ms 125 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 278.521 ms 127 - 141 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 156.352 ms 129 - 132 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 132.132 ms 255 - 255 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 70.387 ms 117 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 70.387 ms 117 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 57.948 ms 128 - 140 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 60.344 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 132.481 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 97.324 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 272.234 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 165.301 ms 0 - 56 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 450.308 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 128.92 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 155.24 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 155.24 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 155.24 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 272.234 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 154.419 ms 1 - 55 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 132.481 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 70.225 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 450.308 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 200.051 ms 1 - 6 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 70.225 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 57.732 ms 1 - 9 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 60.864 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 132.173 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 97.22 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 272.938 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 164.919 ms 0 - 56 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 451.58 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 129.515 ms 1 - 62 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 154.182 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 154.182 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 154.182 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 272.938 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 154.969 ms 0 - 55 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 132.173 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 70.647 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 451.58 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 200.183 ms 1 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 70.647 ms 1 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 57.697 ms 1 - 10 MB NPU

License

  • The license for the original implementation of Whisper-Small 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