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 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.50, ONNX Runtime 1.27.1 | 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 | 3.34 ms | 15 - 24 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.621 ms | 21 - 32 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 2.607 ms | 17 - 17 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 5.161 ms | 267 - 267 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.465 ms | 23 - 35 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.186 ms | 21 - 36 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 19.129 ms | 15 - 35 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.876 ms | 13 - 34 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.966 ms | 0 - 304 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 7.186 ms | 21 - 36 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.569 ms | 12 - 32 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.161 ms | 267 - 267 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 28.596 ms | 16 - 26 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.591 ms | 15 - 25 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.621 ms | 21 - 32 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.591 ms | 15 - 25 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.294 ms | 17 - 25 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.556 ms | 16 - 25 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 3.101 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 5.364 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.449 ms | 16 - 24 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.048 ms | 16 - 31 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.165 ms | 12 - 33 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.742 ms | 16 - 37 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.865 ms | 16 - 18 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 | 7.048 ms | 16 - 31 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.475 ms | 14 - 35 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.364 ms | 17 - 17 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 23.288 ms | 16 - 22 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.508 ms | 16 - 22 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.556 ms | 16 - 25 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 7.27 ms | 14 - 20 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.508 ms | 16 - 22 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.281 ms | 17 - 24 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.546 ms | 17 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 3.116 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 5.509 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.409 ms | 16 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.112 ms | 16 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.475 ms | 11 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 6.734 ms | 16 - 37 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.841 ms | 16 - 18 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 | 7.112 ms | 16 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.442 ms | 14 - 35 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.509 ms | 17 - 17 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 22.079 ms | 12 - 19 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.56 ms | 16 - 22 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.546 ms | 17 - 25 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 7.322 ms | 14 - 20 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.56 ms | 16 - 22 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 133.546 ms | 31 - 44 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 154.002 ms | 32 - 43 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 125.85 ms | 32 - 32 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 271.456 ms | 655 - 655 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 188.4 ms | 32 - 44 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 368.085 ms | 31 - 46 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1423.906 ms | 4 - 7 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 243.071 ms | 31 - 35 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 275.109 ms | 0 - 770 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 368.085 ms | 31 - 46 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 250.737 ms | 31 - 34 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 271.456 ms | 655 - 655 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5848.889 ms | 3 - 14 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 489.492 ms | 16 - 28 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 154.002 ms | 32 - 43 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 489.492 ms | 16 - 28 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 121.589 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 150.033 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 127.169 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 272.533 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 188.329 ms | 1 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 369.244 ms | 2 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1402.003 ms | 3 - 20 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 242.916 ms | 1 - 18 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 269.687 ms | 1 - 17 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 | 369.244 ms | 2 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 250.834 ms | 3 - 20 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 272.533 ms | 1 - 1 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5294.918 ms | 2 - 14 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 483.3 ms | 0 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 150.033 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 352.034 ms | 1 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 483.3 ms | 0 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 121.547 ms | 3 - 12 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 151.265 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 127.102 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 271.638 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 188.765 ms | 3 - 11 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 366.407 ms | 1 - 17 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1401.568 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 243.811 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 270.431 ms | 1 - 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 | 366.407 ms | 1 - 17 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 250.407 ms | 1 - 18 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 271.638 ms | 1 - 1 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5299.707 ms | 2 - 14 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 485.833 ms | 1 - 8 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 151.265 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 350.408 ms | 1 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 485.833 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.