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, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 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™ 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-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® X2 Elite 4.834 ms 33 - 33 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 8.009 ms 401 - 401 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 8.094 ms 42 - 55 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 16.463 ms 42 - 56 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 12.067 ms 33 - 70 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.865 ms 34 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 16.463 ms 42 - 56 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 10.957 ms 33 - 69 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 8.009 ms 401 - 401 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 6.742 ms 21 - 32 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 6.742 ms 21 - 32 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 6.297 ms 22 - 34 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 5.279 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 8.471 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 7.961 ms 33 - 41 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 16.314 ms 33 - 43 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 12.432 ms 33 - 73 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.968 ms 33 - 38 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 16.314 ms 33 - 43 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 11.67 ms 33 - 72 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 8.471 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 6.7 ms 4 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 11.693 ms 25 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 6.7 ms 4 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 6.28 ms 25 - 34 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 5.316 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 8.464 ms 33 - 33 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 7.978 ms 34 - 41 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 16.448 ms 12 - 22 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 12.489 ms 33 - 73 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.863 ms 33 - 35 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® QCS8450 16.448 ms 12 - 22 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 10.932 ms 33 - 72 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 8.464 ms 33 - 33 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 6.713 ms 17 - 30 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 11.674 ms 25 - 30 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 6.713 ms 17 - 30 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 6.266 ms 25 - 35 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 274.731 ms 65 - 65 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 626.772 ms 1677 - 1677 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 469.381 ms 64 - 74 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 1304.317 ms 2 - 14 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 814.08 ms 1 - 5 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 628.304 ms 0 - 1793 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 1304.317 ms 2 - 14 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 857.368 ms 1 - 5 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 626.772 ms 1677 - 1677 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 407.475 ms 64 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 407.475 ms 64 - 73 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 279.077 ms 63 - 72 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 272.932 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 627.015 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 466.402 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 1292.397 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 816.789 ms 1 - 33 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 625.702 ms 1 - 4 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 1292.397 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 751.72 ms 1 - 32 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 627.015 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 409.206 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 876.889 ms 1 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 409.206 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 274.154 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 269.518 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 627.477 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 465.981 ms 1 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 1296.405 ms 1 - 16 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 816.127 ms 1 - 34 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 627.631 ms 1 - 6 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® QCS8450 1296.405 ms 1 - 16 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 751.949 ms 1 - 32 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 627.477 ms 1 - 1 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 399.892 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 877.048 ms 1 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 399.892 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 267.113 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