Hugging Face's logo

qualcomm
/
Whisper-Small-Quantized

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Small-Quantized: Optimized for Qualcomm Devices

We have applied w8a16 quantization to significantly enhance performance and efficiency. 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-Quantized 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-Quantized 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 w8a16 Snapdragon® X2 Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Whisper-Small-Quantized 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-Quantized 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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 3.784 ms 33 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 7.435 ms 186 - 186 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 6.021 ms 38 - 51 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 10.115 ms 37 - 51 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 9.081 ms 26 - 60 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.014 ms 30 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 10.115 ms 37 - 51 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 8.874 ms 24 - 57 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.435 ms 186 - 186 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 38.739 ms 38 - 50 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 10.577 ms 29 - 38 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 4.67 ms 27 - 40 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 4.67 ms 27 - 40 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.945 ms 23 - 35 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.577 ms 29 - 38 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 4.236 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 7.312 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 5.971 ms 30 - 38 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 8.87 ms 25 - 61 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.875 ms 31 - 36 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 8.923 ms 22 - 32 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 8.923 ms 22 - 32 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 8.923 ms 22 - 32 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 8.703 ms 27 - 62 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.312 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 35.645 ms 25 - 32 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 10.332 ms 29 - 36 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 4.617 ms 23 - 35 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 12.835 ms 30 - 40 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 4.617 ms 23 - 35 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.899 ms 24 - 33 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 10.332 ms 29 - 36 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 4.303 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 7.661 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 5.99 ms 30 - 38 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 8.892 ms 26 - 62 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.861 ms 30 - 32 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 8.941 ms 29 - 38 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 8.941 ms 29 - 38 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 8.941 ms 29 - 38 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 8.719 ms 25 - 60 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.661 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 37.522 ms 24 - 31 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 10.437 ms 30 - 37 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 4.646 ms 30 - 39 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 12.812 ms 12 - 21 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 4.646 ms 30 - 39 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.92 ms 25 - 34 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 10.437 ms 30 - 37 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 156.334 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 304.544 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 266.176 ms 64 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 356.619 ms 55 - 68 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 306.571 ms 62 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 395.104 ms 0 - 130 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 356.619 ms 55 - 68 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 296.401 ms 63 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 304.544 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 4150.712 ms 14 - 25 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 477.162 ms 31 - 41 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 225.467 ms 64 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 225.467 ms 64 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 174.034 ms 64 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 477.162 ms 31 - 41 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 156.476 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 301.183 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 265.977 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 305.802 ms 0 - 30 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 391.454 ms 1 - 2 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 315.467 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 315.467 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 315.467 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 297.037 ms 0 - 29 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 301.183 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 3782.122 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 476.353 ms 3 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 227.454 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 517.669 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 227.454 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 210.189 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 476.353 ms 3 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 154.093 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 306.142 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 273.876 ms 3 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 306.17 ms 0 - 29 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 383.992 ms 1 - 3 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 315.503 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 315.503 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 315.503 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 296.062 ms 0 - 29 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 306.142 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 3994.742 ms 1 - 13 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 472.326 ms 1 - 7 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 223.407 ms 1 - 14 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 516.134 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 223.407 ms 1 - 14 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 181.617 ms 1 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 472.326 ms 1 - 7 MB NPU

License

  • The license for the original implementation of Whisper-Small-Quantized 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