Whisper-Medium-Quantized: Optimized for Qualcomm Devices
We have applied w8a16 quantization to significantly enhance performance and efficiency. HuggingFace Whisper-Medium ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text. 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-Medium-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-Medium-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-Medium-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-Medium-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-medium
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 | 11.793 ms | 77 - 91 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.486 ms | 65 - 78 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 10.5 ms | 80 - 80 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 20.486 ms | 425 - 425 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 17.14 ms | 100 - 113 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 30.122 ms | 80 - 96 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 64.305 ms | 79 - 162 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 25.03 ms | 77 - 161 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.705 ms | 80 - 83 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 30.122 ms | 80 - 96 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.592 ms | 79 - 162 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.486 ms | 425 - 425 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 127.171 ms | 81 - 93 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 30.421 ms | 63 - 74 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.486 ms | 65 - 78 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 30.421 ms | 63 - 74 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.316 ms | 74 - 86 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.42 ms | 23 - 36 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 11.347 ms | 80 - 80 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 20.62 ms | 80 - 80 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 16.939 ms | 62 - 73 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 27.334 ms | 79 - 97 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 64.148 ms | 77 - 168 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 24.433 ms | 76 - 167 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.27 ms | 58 - 60 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 27.334 ms | 79 - 97 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.647 ms | 76 - 167 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.62 ms | 80 - 80 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 85.332 ms | 18 - 27 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 30.419 ms | 30 - 39 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.42 ms | 23 - 36 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 25.949 ms | 74 - 81 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 30.419 ms | 30 - 39 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.348 ms | 77 - 92 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.336 ms | 6 - 16 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 11.375 ms | 80 - 80 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 20.242 ms | 80 - 80 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 16.746 ms | 53 - 62 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 28.289 ms | 79 - 96 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 64.799 ms | 80 - 170 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 23.728 ms | 77 - 169 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.301 ms | 54 - 56 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 28.289 ms | 79 - 96 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.28 ms | 75 - 166 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.242 ms | 80 - 80 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 130.965 ms | 19 - 27 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 30.51 ms | 42 - 49 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.336 ms | 6 - 16 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 26.123 ms | 76 - 83 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 30.51 ms | 42 - 49 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 70.034 ms | 153 - 166 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 99.047 ms | 155 - 167 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 76.187 ms | 263 - 263 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 168.672 ms | 364 - 364 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 122.009 ms | 152 - 165 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 234.851 ms | 149 - 164 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 675.742 ms | 81 - 86 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 156.679 ms | 148 - 153 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 172.294 ms | 0 - 386 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 234.851 ms | 149 - 164 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 162.663 ms | 151 - 155 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 168.672 ms | 364 - 364 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2315.627 ms | 5 - 16 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 262.798 ms | 127 - 137 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 99.047 ms | 155 - 167 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 262.798 ms | 127 - 137 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 69.816 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 97.394 ms | 1 - 14 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 76.629 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 169.383 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 123.409 ms | 1 - 14 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 236.546 ms | 1 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 678.002 ms | 0 - 73 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 156.631 ms | 0 - 74 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 170.441 ms | 1 - 2 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 236.546 ms | 1 - 11 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 161.13 ms | 0 - 73 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 169.383 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2257.856 ms | 0 - 8 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 264.483 ms | 2 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 97.394 ms | 1 - 14 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 219.298 ms | 1 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 264.483 ms | 2 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 71.39 ms | 0 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 97.537 ms | 0 - 8 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 76.133 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 170.54 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 122.47 ms | 1 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 226.372 ms | 0 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 680.19 ms | 0 - 73 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 157.516 ms | 0 - 74 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 169.872 ms | 1 - 3 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 226.372 ms | 0 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 161.163 ms | 0 - 73 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 170.54 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2269.168 ms | 0 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 271.879 ms | 2 - 9 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 97.537 ms | 0 - 8 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 218.783 ms | 1 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 271.879 ms | 2 - 9 MB | NPU |
License
- The license for the original implementation of Whisper-Medium-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.