Hugging Face's logo

qualcomm
/
Whisper-Tiny

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Tiny: Optimized for Qualcomm Devices

HuggingFace Whisper-Tiny 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-Tiny 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-Tiny 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® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit Whisper-Tiny 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-Tiny 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-tiny
  • Model size (decoder) (float): 109 MB
  • Model size (encoder) (float): 35.9 MB
  • Number of parameters (decoder): 28.4M
  • Number of parameters (encoder): 9.39M

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 For Galaxy Mobile 1.531 ms 0 - 11 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.555 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 1.432 ms 10 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 2.212 ms 83 - 83 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 1.96 ms 6 - 19 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 2.597 ms 13 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 3.354 ms 10 - 24 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.494 ms 0 - 86 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 2.597 ms 13 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 3.142 ms 10 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.212 ms 83 - 83 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 1.555 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.514 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 1.591 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 1.826 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 2.313 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 1.873 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 2.496 ms 1 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 3.234 ms 10 - 24 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.429 ms 10 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 3.164 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 3.164 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 2.496 ms 1 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 3.075 ms 10 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 2.313 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 1.591 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 2.798 ms 8 - 13 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.516 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 1.519 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.868 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.498 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 1.882 ms 0 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.495 ms 1 - 11 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 3.238 ms 10 - 24 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.434 ms 1 - 3 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 3.236 ms 5 - 14 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 3.236 ms 5 - 14 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.495 ms 1 - 11 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 3.098 ms 10 - 23 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.498 ms 10 - 10 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.519 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 2.805 ms 10 - 15 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 11.86 ms 21 - 28 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 13.943 ms 21 - 27 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 18.933 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 24.751 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 17.98 ms 21 - 28 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 35.386 ms 19 - 28 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 27.837 ms 19 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 24.009 ms 12 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 35.386 ms 19 - 28 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 27.818 ms 20 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 24.751 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 13.943 ms 21 - 27 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 11.85 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 14.048 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 12.166 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 24.827 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 17.853 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 34.622 ms 0 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 27.733 ms 0 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 23.848 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 28.644 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 28.644 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 34.622 ms 0 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 26.935 ms 0 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 24.827 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 14.048 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 34.454 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 11.855 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 13.991 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 12.026 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 25.033 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 17.855 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 35.067 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 27.76 ms 0 - 13 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 23.866 ms 7 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 28.668 ms 0 - 6 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 28.668 ms 0 - 6 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 35.067 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 27.114 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 25.033 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 13.991 ms 1 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 34.471 ms 0 - 5 MB NPU

License

  • The license for the original implementation of Whisper-Tiny 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