Hugging Face's logo

qualcomm
/
Whisper-Large-V3-Turbo-Quantized

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

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

We have applied w8a16 quantization to significantly enhance performance and efficiency. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3, with the number of decoding layers reduced from 32 to 4. 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-Quantized 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-Quantized 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 w8a16 Snapdragon® X2 Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45 Download
PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® X2 Elite QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® X Elite QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-6690 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.45 Download
VOICE_AI w8a16 Qualcomm® SA7255P QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Whisper-Large-V3-Turbo-Quantized 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-Quantized 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 w8a16 Snapdragon® X2 Elite 2.508 ms 17 - 17 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 5.242 ms 267 - 267 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 4.51 ms 14 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 8.047 ms 21 - 35 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 6.818 ms 14 - 34 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.861 ms 0 - 304 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 8.047 ms 21 - 35 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 6.575 ms 12 - 31 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.242 ms 267 - 267 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 8.519 ms 15 - 25 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 3.626 ms 23 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 3.626 ms 23 - 36 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.295 ms 15 - 25 MB NPU
decoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 8.519 ms 15 - 25 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 3.163 ms 17 - 17 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 5.319 ms 17 - 17 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 4.468 ms 16 - 24 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 6.694 ms 16 - 37 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 9.124 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 6.622 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 6.622 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 6.622 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 6.467 ms 14 - 34 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.319 ms 17 - 17 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 8.444 ms 16 - 23 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 3.581 ms 17 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 9.124 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 3.581 ms 17 - 29 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.288 ms 17 - 26 MB NPU
decoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 8.444 ms 16 - 23 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 3.193 ms 17 - 17 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 5.604 ms 17 - 17 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 4.514 ms 16 - 24 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 6.657 ms 16 - 37 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 9.106 ms 17 - 26 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 6.669 ms 17 - 26 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 6.669 ms 17 - 26 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 6.669 ms 17 - 26 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 6.752 ms 14 - 34 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.604 ms 17 - 17 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 8.438 ms 16 - 22 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 3.569 ms 16 - 29 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 9.106 ms 17 - 26 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 3.569 ms 16 - 29 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.282 ms 17 - 25 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 8.438 ms 16 - 22 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X2 Elite 691.376 ms 33 - 33 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® X Elite 1360.218 ms 742 - 742 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1421.004 ms 2 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 1527.758 ms 2 - 15 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 1346.781 ms 1 - 5 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1763.356 ms 0 - 770 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® QCS8450 1527.758 ms 2 - 15 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 1295.023 ms 4 - 7 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 1360.218 ms 742 - 742 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 2227.623 ms 2 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 1232.326 ms 1 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Mobile 1232.326 ms 1 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1167.227 ms 1 - 14 MB NPU
encoder PRECOMPILED_QNN_ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 2227.623 ms 2 - 12 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X2 Elite 691.669 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® X Elite 1362.647 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Gen 3 Mobile 1340.577 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 1346.064 ms 0 - 18 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-8275 2354.47 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8775P 1433.901 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8650P 1433.901 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA8255P 1433.901 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-9075 1294.84 ms 1 - 18 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ IQ-X7181 1362.647 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-7790 2228.516 ms 0 - 7 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® Dragonwing™ Q-8750 1220.377 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Qualcomm® SA7255P 2354.47 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Mobile 1220.377 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1160.918 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY w8a16 Snapdragon® 7 Gen 4 Mobile 2228.516 ms 0 - 7 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 693.843 ms 1 - 1 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 1344.22 ms 1 - 1 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 3 Mobile 1356.408 ms 1 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 1348.186 ms 0 - 18 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 2350.399 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 1434.489 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 1434.489 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 1434.489 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 1294.612 ms 3 - 20 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 1344.22 ms 1 - 1 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-7790 2215.762 ms 0 - 7 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 1151.383 ms 1 - 14 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 2350.399 ms 1 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Mobile 1151.383 ms 1 - 14 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1132.26 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 7 Gen 4 Mobile 2215.762 ms 0 - 7 MB NPU

License

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