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™ 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™ 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™ 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:

  • Model checkpoint: openai/whisper-small
  • Input resolution: 80x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 3.814 ms 33 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 7.187 ms 186 - 186 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 6.172 ms 38 - 50 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 10.081 ms 38 - 52 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.914 ms 26 - 29 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 10.081 ms 38 - 52 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 8.808 ms 24 - 57 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.187 ms 186 - 186 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 38.564 ms 38 - 49 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 10.497 ms 28 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 4.7 ms 27 - 35 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 4.7 ms 27 - 35 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.937 ms 23 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.497 ms 28 - 36 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 4.224 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 7.3 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 6.076 ms 30 - 39 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8275 12.688 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.823 ms 30 - 32 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 8.822 ms 26 - 35 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 8.822 ms 26 - 35 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 8.822 ms 26 - 35 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 8.648 ms 25 - 60 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.3 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 29.771 ms 30 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 10.355 ms 28 - 34 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 4.637 ms 29 - 38 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 12.688 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 4.637 ms 29 - 38 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.976 ms 24 - 34 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 10.355 ms 28 - 34 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 4.247 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 7.475 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 5.942 ms 23 - 31 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8275 12.78 ms 21 - 30 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.919 ms 30 - 33 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 8.956 ms 10 - 20 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 8.956 ms 10 - 20 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 8.956 ms 10 - 20 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 8.656 ms 25 - 60 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.475 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 35.073 ms 30 - 37 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 10.455 ms 28 - 34 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 4.648 ms 19 - 32 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 12.78 ms 21 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 4.648 ms 19 - 32 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.947 ms 23 - 32 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 10.455 ms 28 - 34 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 156.044 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 306.451 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 274.961 ms 63 - 76 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 305.2 ms 63 - 76 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 405.773 ms 55 - 57 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 305.2 ms 63 - 76 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 296.762 ms 63 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 306.451 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 4499.151 ms 2 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 489.603 ms 31 - 42 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 229.54 ms 63 - 77 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 229.54 ms 63 - 77 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 174.716 ms 64 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 489.603 ms 31 - 42 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 156.637 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 304.122 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 268.159 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8275 518.717 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 366.468 ms 1 - 32 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 315.857 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 315.857 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 315.857 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 297.094 ms 0 - 29 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 304.122 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 3951.844 ms 0 - 7 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 481.373 ms 1 - 7 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 228.931 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 518.717 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 228.931 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 174.788 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 481.373 ms 1 - 7 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 157.112 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 301.766 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 273.236 ms 1 - 7 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8275 513.457 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 388.741 ms 1 - 13 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 316.173 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 316.173 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 316.173 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 295.639 ms 0 - 29 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 301.766 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 3948.757 ms 1 - 13 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 480.048 ms 1 - 7 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 231.703 ms 1 - 13 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 513.457 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 231.703 ms 1 - 13 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 174.997 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 480.048 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