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™ IQ-8275 QAIRT 2.45 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™ IQ-8275 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™ IQ-8275 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:

  • 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® X2 Elite 1.29 ms 10 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 2.076 ms 84 - 84 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 1.908 ms 13 - 20 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 2.674 ms 13 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 3.329 ms 10 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.522 ms 10 - 12 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 2.674 ms 13 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 3.155 ms 10 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.076 ms 84 - 84 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 1.577 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 1.577 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.504 ms 1 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 1.725 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 2.348 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 2.662 ms 9 - 18 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 3.226 ms 10 - 24 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 4.528 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.455 ms 10 - 11 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 3.244 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 3.244 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 3.244 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 2.662 ms 9 - 18 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 3.127 ms 10 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 2.348 ms 10 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 1.555 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 4.528 ms 10 - 19 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 2.933 ms 8 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 1.555 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 1.496 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.727 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.293 ms 10 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 1.873 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.646 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 3.216 ms 10 - 24 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 4.57 ms 10 - 18 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.444 ms 10 - 11 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 3.257 ms 8 - 18 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 3.257 ms 8 - 18 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 3.257 ms 8 - 18 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.646 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 3.036 ms 10 - 23 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.293 ms 10 - 10 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.568 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 4.57 ms 10 - 18 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 2.943 ms 8 - 13 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 1.568 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 1.494 ms 0 - 10 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 12.674 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 26.038 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 20.041 ms 20 - 26 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 44.073 ms 19 - 31 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 30.901 ms 19 - 22 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.263 ms 13 - 34 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 44.073 ms 19 - 31 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 29.429 ms 19 - 22 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 26.038 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 15.292 ms 22 - 29 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 15.292 ms 22 - 29 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 12.522 ms 21 - 28 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 12.912 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 26.068 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 19.776 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 43.778 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 30.608 ms 0 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 72.901 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.367 ms 1 - 2 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 28.631 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 28.631 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 28.631 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 43.778 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 29.238 ms 2 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 26.068 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 15.361 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 72.901 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 42.369 ms 0 - 6 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 15.361 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 12.521 ms 1 - 10 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 12.987 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 26.192 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 19.94 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 44.038 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 30.776 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 73.04 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 25.138 ms 1 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 28.668 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 28.668 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 28.668 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 44.038 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 28.98 ms 0 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 26.192 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 15.51 ms 1 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 73.04 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 42.344 ms 0 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 15.51 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 12.543 ms 1 - 10 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