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.

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 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 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 Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 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 Qualcomm® QCS9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 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:

  • Model checkpoint: openai/whisper-small
  • Input resolution: 80x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Number of parameters (encoder): 102M
  • Model size (encoder) (float): 391 MB
  • Number of parameters (decoder): 139M
  • Model size (decoder) (float): 533 MB

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 Mobile 7.217 ms 75 - 85 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 8.306 ms 56 - 68 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.971 ms 286 - 286 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 10.519 ms 285 - 285 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 10.519 ms 285 - 285 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 9.769 ms 75 - 81 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 12.083 ms 58 - 60 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 13.4 ms 60 - 122 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 8.306 ms 56 - 68 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 7.357 ms 60 - 70 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 8.298 ms 33 - 46 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 7.077 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 10.021 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 10.021 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 9.718 ms 29 - 37 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 18.875 ms 43 - 51 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 12.13 ms 59 - 61 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 13.6 ms 60 - 69 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 13.6 ms 60 - 69 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 13.6 ms 60 - 69 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 13.439 ms 62 - 130 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 17.61 ms 60 - 70 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 18.875 ms 43 - 51 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 14.312 ms 45 - 51 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 8.298 ms 33 - 46 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 46.529 ms 127 - 137 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 59.45 ms 128 - 135 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 47.602 ms 202 - 202 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 115.856 ms 201 - 201 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 115.856 ms 201 - 201 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 81.819 ms 106 - 112 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 114.075 ms 0 - 225 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 136.722 ms 131 - 134 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 59.45 ms 128 - 135 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 57.798 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 69.981 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 59.819 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 131.943 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 131.943 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 97.488 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 449.387 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 129.422 ms 1 - 4 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 155.406 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 155.406 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 155.406 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 154.824 ms 0 - 55 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 271.772 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 449.387 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 200.103 ms 1 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 69.981 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