Hugging Face's logo

qualcomm
/
Whisper-Large-V3-Turbo

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Large-V3-Turbo: Optimized for Qualcomm Devices

Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation. 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-Large-V3-Turbo 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-Large-V3-Turbo 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 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-Large-V3-Turbo 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-Large-V3-Turbo on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.speech_recognition

Model Stats:

  • Model checkpoint: openai/whisper-large-v3-turbo
  • Input resolution: 128x3000 (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 float Snapdragon® X2 Elite 4.882 ms 33 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 8.15 ms 400 - 400 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 8.045 ms 42 - 55 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.911 ms 34 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 10.939 ms 33 - 69 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.15 ms 400 - 400 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 6.787 ms 13 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 6.787 ms 13 - 23 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 6.428 ms 21 - 32 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 5.306 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 8.42 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 7.906 ms 35 - 42 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 16.361 ms 14 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.905 ms 33 - 39 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 16.361 ms 14 - 23 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 10.877 ms 33 - 72 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 8.42 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 6.694 ms 4 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 11.672 ms 25 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 6.694 ms 4 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 6.262 ms 25 - 34 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 5.285 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 8.449 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 7.997 ms 35 - 42 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.748 ms 33 - 37 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 11.218 ms 16 - 25 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 11.218 ms 16 - 25 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 11.218 ms 16 - 25 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 11.274 ms 33 - 72 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 8.449 ms 33 - 33 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 6.74 ms 4 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 11.687 ms 25 - 30 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 6.74 ms 4 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 6.261 ms 21 - 30 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 269.722 ms 65 - 65 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 626.907 ms 1677 - 1677 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 468.575 ms 64 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 664.351 ms 1 - 1793 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 752.965 ms 9 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 626.907 ms 1677 - 1677 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 407.639 ms 63 - 74 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 407.639 ms 63 - 74 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 271.209 ms 63 - 74 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 270.431 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 629.907 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 466.374 ms 2 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 1282.784 ms 1 - 16 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 626.55 ms 1 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 1282.784 ms 1 - 16 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 753.291 ms 1 - 32 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 629.907 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 406.559 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 877.713 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 406.559 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 267.72 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 269.608 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 630.062 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 465.632 ms 2 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 624.768 ms 1 - 4 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 760.379 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 760.379 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 760.379 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 751.984 ms 1 - 32 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 630.062 ms 1 - 1 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 403.197 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 877.479 ms 1 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 403.197 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 272.048 ms 0 - 9 MB NPU

License

  • The license for the original implementation of Whisper-Large-V3-Turbo 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