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.

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 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 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 Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 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® 8 Elite Gen 5 Mobile 6.142 ms 42 - 52 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 6.626 ms 21 - 32 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 4.491 ms 400 - 400 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 8.349 ms 399 - 399 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 8.349 ms 399 - 399 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 7.458 ms 43 - 54 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.715 ms 32 - 34 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.333 ms 33 - 69 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 6.626 ms 21 - 32 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 6.274 ms 33 - 43 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 6.741 ms 8 - 21 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 5.177 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 8.361 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 8.361 ms 33 - 33 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 7.975 ms 33 - 42 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 9.913 ms 26 - 28 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.888 ms 33 - 72 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 16.368 ms 33 - 42 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 11.617 ms 25 - 31 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 6.741 ms 8 - 21 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 258.307 ms 62 - 70 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 318.348 ms 62 - 74 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 252.718 ms 1276 - 1276 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 584.975 ms 1274 - 1274 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 584.975 ms 1274 - 1274 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 425.604 ms 63 - 74 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 590.412 ms 0 - 1281 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 699.327 ms 63 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 318.348 ms 62 - 74 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 273.011 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 411.025 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 270.752 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 627.821 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 627.821 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 469.452 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 624.694 ms 1 - 2 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 752.361 ms 1 - 32 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 1302.347 ms 1 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 876.857 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 411.025 ms 1 - 14 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