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® X2 Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 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 Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 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 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 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:

  • Model checkpoint: openai/whisper-tiny
  • Input resolution: 80x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Number of parameters (encoder): 9.39M
  • Model size (encoder) (float): 35.9 MB
  • Number of parameters (decoder): 28.4M
  • Model size (decoder) (float): 109 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 1.324 ms 10 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 2.103 ms 84 - 84 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 1.922 ms 13 - 24 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 2.774 ms 13 - 28 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.497 ms 10 - 12 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 2.774 ms 13 - 28 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 3.119 ms 10 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.103 ms 84 - 84 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 1.581 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 1.581 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.508 ms 1 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 1.761 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 2.356 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 1.897 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 2.656 ms 10 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8275 4.557 ms 10 - 18 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.449 ms 10 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 3.214 ms 4 - 14 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 3.214 ms 4 - 14 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 3.214 ms 4 - 14 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 2.656 ms 10 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 3.03 ms 10 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 2.356 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 1.567 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 4.557 ms 10 - 18 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 2.964 ms 8 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 1.567 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 1.501 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.693 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.454 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 1.855 ms 0 - 7 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.626 ms 3 - 13 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8275 4.561 ms 10 - 19 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.448 ms 10 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 3.235 ms 0 - 10 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 3.235 ms 0 - 10 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 3.235 ms 0 - 10 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.626 ms 3 - 13 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 3.035 ms 10 - 23 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.454 ms 10 - 10 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.544 ms 0 - 8 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 4.561 ms 10 - 19 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 2.933 ms 8 - 13 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 1.544 ms 0 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 1.494 ms 0 - 9 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 12.679 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 26.159 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 19.996 ms 21 - 27 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 43.953 ms 19 - 32 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.216 ms 12 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 43.953 ms 19 - 32 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 29.087 ms 21 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 26.159 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 15.369 ms 20 - 27 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 15.369 ms 20 - 27 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 12.522 ms 19 - 26 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 12.948 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 26.103 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 19.973 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 43.779 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8275 73.057 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.337 ms 0 - 5 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 28.657 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 28.657 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 28.657 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 43.779 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 29.111 ms 0 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 26.103 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 15.252 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 73.057 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 42.422 ms 0 - 6 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 15.252 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 12.513 ms 1 - 9 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 12.997 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 26.181 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 19.818 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 44.078 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8275 72.959 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.244 ms 1 - 6 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 28.661 ms 2 - 7 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 28.661 ms 2 - 7 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 28.661 ms 2 - 7 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 44.078 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 38.473 ms 2 - 13 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 26.181 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 15.232 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 72.959 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 42.386 ms 0 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 15.232 ms 1 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 12.516 ms 1 - 9 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