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® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | QAIRT 2.50 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® X2 Elite | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® X Elite | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® SA8775P | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® SA7255P | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Qualcomm® SA8295P | QAIRT 2.50 | Download |
| VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.50 | 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® 8 Elite Gen 5 For Galaxy Mobile | 3.289 ms | 15 - 29 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.63 ms | 23 - 30 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 2.512 ms | 17 - 17 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 5.129 ms | 267 - 267 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.545 ms | 22 - 34 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.206 ms | 21 - 35 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.72 ms | 15 - 35 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.837 ms | 14 - 34 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.931 ms | 0 - 304 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 7.206 ms | 21 - 35 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.568 ms | 12 - 32 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.129 ms | 267 - 267 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 22.582 ms | 15 - 25 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.596 ms | 15 - 24 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.63 ms | 23 - 30 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.596 ms | 15 - 24 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.288 ms | 17 - 25 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.542 ms | 16 - 23 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 2.975 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 5.39 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.417 ms | 16 - 24 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.079 ms | 16 - 32 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.465 ms | 16 - 36 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.738 ms | 14 - 35 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.756 ms | 16 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 6.693 ms | 17 - 26 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 6.693 ms | 17 - 26 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 7.079 ms | 16 - 32 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.443 ms | 14 - 35 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.39 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 21.77 ms | 16 - 22 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.528 ms | 16 - 22 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.542 ms | 16 - 23 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 7.292 ms | 14 - 20 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.528 ms | 16 - 22 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.368 ms | 17 - 26 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.569 ms | 15 - 23 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 3.055 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 5.519 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.45 ms | 16 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.095 ms | 16 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.947 ms | 16 - 36 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.738 ms | 14 - 35 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.848 ms | 16 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 6.634 ms | 16 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 6.634 ms | 16 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 7.095 ms | 16 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.454 ms | 16 - 37 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.519 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 22.162 ms | 16 - 23 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.554 ms | 16 - 23 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.569 ms | 15 - 23 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 7.267 ms | 17 - 22 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.554 ms | 16 - 23 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 124.968 ms | 32 - 45 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 156.908 ms | 32 - 44 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 126.291 ms | 32 - 32 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 271.635 ms | 655 - 655 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 191.045 ms | 31 - 44 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 382.801 ms | 31 - 46 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1414.533 ms | 2 - 5 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 242.642 ms | 31 - 35 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 270.822 ms | 0 - 770 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 382.801 ms | 31 - 46 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 251.44 ms | 32 - 35 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 271.635 ms | 655 - 655 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5859.698 ms | 3 - 14 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 486.976 ms | 16 - 27 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 156.908 ms | 32 - 44 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 486.976 ms | 16 - 27 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 121.092 ms | 3 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 150.738 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 126.124 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 271.987 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 187.464 ms | 12 - 19 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 371.727 ms | 0 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1405.044 ms | 1 - 18 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 242.465 ms | 1 - 18 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 272.275 ms | 1 - 16 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 1433.464 ms | 1 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 1433.464 ms | 1 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 371.727 ms | 0 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 250.875 ms | 1 - 18 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 271.987 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5340.157 ms | 2 - 14 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 484.306 ms | 0 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 150.738 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 350.759 ms | 1 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 484.306 ms | 0 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 121.75 ms | 1 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 150.431 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 128.433 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 271.677 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 188.258 ms | 1 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 379.523 ms | 1 - 11 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1401.381 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 242.77 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 272.133 ms | 0 - 3 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 1434.77 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 1434.77 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 379.523 ms | 1 - 11 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 251.22 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 271.677 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5425.874 ms | 2 - 14 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 487.874 ms | 1 - 8 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 150.431 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 350.571 ms | 1 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 487.874 ms | 1 - 8 MB | NPU |
License
- The license for the original implementation of Whisper-Large-V3-Turbo-Quantized can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.