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.

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® 8 Elite Gen 5 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 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® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 QAIRT 2.45 Download
VOICE_AI 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® QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® QCM6690 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® QCS9075 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® 8 Elite Gen 5 Mobile 3.975 ms 30 - 40 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 4.785 ms 25 - 37 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 3.778 ms 185 - 185 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 8.087 ms 185 - 185 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 8.087 ms 185 - 185 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 6.333 ms 36 - 43 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 8.343 ms 31 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 9.073 ms 30 - 63 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 30.182 ms 28 - 38 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.785 ms 25 - 37 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.931 ms 30 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.931 ms 30 - 36 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.914 ms 30 - 41 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 4.647 ms 22 - 31 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 4.286 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 7.335 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 7.335 ms 30 - 30 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 5.91 ms 30 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 (Proxy) 12.694 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 7.808 ms 30 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 8.868 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 8.868 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 8.868 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 8.682 ms 25 - 60 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 30.02 ms 30 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 12.694 ms 12 - 20 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.647 ms 22 - 31 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 10.471 ms 30 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 10.471 ms 30 - 37 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.905 ms 30 - 40 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 4.6 ms 25 - 34 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 4.232 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 7.317 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 7.317 ms 30 - 30 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 6.033 ms 30 - 38 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8275 (Proxy) 12.763 ms 28 - 37 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8550 (Proxy) 7.811 ms 30 - 32 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 8.923 ms 30 - 40 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 8.923 ms 30 - 40 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 8.923 ms 30 - 40 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS9075 8.634 ms 25 - 60 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCM6690 29.834 ms 30 - 37 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 12.763 ms 28 - 37 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 4.6 ms 25 - 34 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 10.481 ms 29 - 36 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 10.481 ms 29 - 36 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 176.504 ms 63 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 198.034 ms 63 - 76 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 156.793 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 266.601 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 266.601 ms 127 - 127 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 239.508 ms 63 - 70 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8550 (Proxy) 339.161 ms 0 - 130 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS9075 255.894 ms 63 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCM6690 4406.598 ms 1 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 198.034 ms 63 - 76 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 463.981 ms 57 - 67 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 463.981 ms 57 - 67 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 175.704 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 224.816 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 157.612 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 303.395 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 303.395 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 266.792 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8275 (Proxy) 518.736 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS8550 (Proxy) 391.748 ms 1 - 3 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 315.091 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 315.091 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 315.091 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCS9075 296.24 ms 1 - 29 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® QCM6690 4378.802 ms 1 - 12 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 518.736 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite For Galaxy Mobile 224.816 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 481.146 ms 1 - 7 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 481.146 ms 1 - 7 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 176.554 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 225.326 ms 1 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 157.176 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 303.118 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 303.118 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 273.885 ms 1 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8275 (Proxy) 516.426 ms 1 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8550 (Proxy) 369.59 ms 1 - 2 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 317.106 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 317.106 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 317.106 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS9075 296.138 ms 0 - 29 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCM6690 4282.667 ms 1 - 12 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 516.426 ms 1 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 225.326 ms 1 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 485.563 ms 0 - 6 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 485.563 ms 0 - 6 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