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® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.30.0 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-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:

  • Input resolution: 128x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Model checkpoint: openai/whisper-large-v3-turbo

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 6.469 ms 21 - 32 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 6.755 ms 19 - 31 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.082 ms 33 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 8.525 ms 401 - 401 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 7.978 ms 44 - 57 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 12.119 ms 33 - 70 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 10.04 ms 0 - 414 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 10.677 ms 33 - 70 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.525 ms 401 - 401 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 6.755 ms 19 - 31 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 6.481 ms 21 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 6.736 ms 4 - 16 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 5.335 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 8.789 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 7.811 ms 33 - 41 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 11.714 ms 33 - 73 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 11.08 ms 21 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 11.08 ms 21 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 10.489 ms 33 - 72 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 8.789 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 6.736 ms 4 - 16 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 11.864 ms 24 - 29 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 6.452 ms 25 - 34 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 6.738 ms 4 - 16 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 5.501 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 8.723 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 7.783 ms 33 - 41 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 11.43 ms 31 - 41 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 11.949 ms 33 - 73 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.904 ms 33 - 35 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 11.105 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 11.105 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 11.43 ms 31 - 41 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 10.553 ms 33 - 72 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 8.723 ms 33 - 33 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 6.738 ms 4 - 16 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 11.795 ms 23 - 29 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 298.883 ms 63 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 311.948 ms 63 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 251.795 ms 64 - 64 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 561.377 ms 1674 - 1674 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 404.254 ms 63 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 708.093 ms 31 - 36 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 574.58 ms 0 - 1793 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 679.766 ms 62 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 561.377 ms 1674 - 1674 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 311.948 ms 63 - 73 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 282.719 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 305.181 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 257.977 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 562.729 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 401.125 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 707.998 ms 1 - 34 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 761.166 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 761.166 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 677.367 ms 1 - 33 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 562.729 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 305.181 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 743.868 ms 1 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 285.247 ms 1 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 306.753 ms 1 - 14 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 252.702 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 560.118 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 398.607 ms 3 - 16 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 842.293 ms 2 - 16 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 707.095 ms 1 - 34 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 554.525 ms 1 - 4 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 766.234 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 766.234 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 842.293 ms 2 - 16 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 680.391 ms 1 - 33 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 560.118 ms 1 - 1 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 306.753 ms 1 - 14 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 744.887 ms 1 - 7 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