Whisper-Small-Quantized: Optimized for Qualcomm Devices
We have applied w8a16 quantization to significantly enhance performance and efficiency. HuggingFace Whisper-Small 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-Small-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-Small-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-Small-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-Small-Quantized on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.speech_recognition
Model Stats:
- Input resolution: 80x3000 (30 seconds audio)
- Max decoded sequence length: 200 tokens
- Model checkpoint: openai/whisper-small
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 | 3.943 ms | 23 - 34 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.716 ms | 28 - 43 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.706 ms | 33 - 33 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.539 ms | 186 - 186 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.19 ms | 38 - 51 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.539 ms | 37 - 52 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 24.117 ms | 30 - 63 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.144 ms | 25 - 59 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.044 ms | 30 - 33 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 9.539 ms | 37 - 52 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.8 ms | 24 - 58 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.539 ms | 186 - 186 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 28.995 ms | 29 - 40 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.383 ms | 30 - 41 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.716 ms | 28 - 43 MB | NPU |
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.383 ms | 30 - 41 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.917 ms | 25 - 33 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.695 ms | 23 - 31 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.19 ms | 30 - 30 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.464 ms | 30 - 30 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.118 ms | 30 - 38 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.428 ms | 30 - 45 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 23.492 ms | 30 - 66 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.0 ms | 25 - 62 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.997 ms | 29 - 33 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 8.926 ms | 18 - 27 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 8.926 ms | 18 - 27 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 9.428 ms | 30 - 45 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.643 ms | 25 - 61 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.464 ms | 30 - 30 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 29.94 ms | 23 - 29 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.255 ms | 32 - 39 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.695 ms | 23 - 31 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 9.52 ms | 30 - 36 MB | NPU |
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.255 ms | 32 - 39 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.958 ms | 23 - 32 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.682 ms | 30 - 43 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 4.259 ms | 30 - 30 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 7.497 ms | 30 - 30 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.136 ms | 30 - 38 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.401 ms | 30 - 45 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 23.448 ms | 30 - 66 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 8.88 ms | 25 - 61 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.051 ms | 26 - 31 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 9.001 ms | 1 - 11 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 9.001 ms | 1 - 11 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 9.401 ms | 30 - 45 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.659 ms | 25 - 61 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.497 ms | 30 - 30 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 31.465 ms | 32 - 39 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.358 ms | 32 - 39 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.682 ms | 30 - 43 MB | NPU |
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 9.63 ms | 30 - 36 MB | NPU |
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.358 ms | 32 - 39 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 27.369 ms | 63 - 73 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 34.69 ms | 63 - 76 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 27.645 ms | 67 - 67 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 59.497 ms | 108 - 108 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 44.355 ms | 64 - 75 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 79.387 ms | 63 - 78 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 237.404 ms | 63 - 67 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 56.544 ms | 62 - 67 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 60.335 ms | 0 - 114 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 79.387 ms | 63 - 78 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 58.765 ms | 63 - 67 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 59.497 ms | 108 - 108 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 880.115 ms | 38 - 49 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 94.326 ms | 65 - 71 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 34.69 ms | 63 - 76 MB | NPU |
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 94.326 ms | 65 - 71 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 27.189 ms | 1 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 34.353 ms | 1 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 28.097 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 60.435 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 43.884 ms | 1 - 8 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 77.978 ms | 0 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 235.375 ms | 0 - 30 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 56.529 ms | 0 - 30 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 60.123 ms | 0 - 3 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 57.923 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 57.923 ms | 1 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 77.978 ms | 0 - 10 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 58.543 ms | 0 - 30 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 60.435 ms | 0 - 0 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 857.412 ms | 3 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 95.242 ms | 1 - 7 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 34.353 ms | 1 - 9 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 75.986 ms | 0 - 5 MB | NPU |
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 95.242 ms | 1 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 27.293 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 34.275 ms | 1 - 13 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 28.197 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 59.892 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 43.81 ms | 1 - 8 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 1 Mobile | 79.929 ms | 2 - 15 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 235.862 ms | 1 - 30 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 56.341 ms | 0 - 30 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 60.57 ms | 1 - 3 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 57.719 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 57.719 ms | 1 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS8450 | 79.929 ms | 2 - 15 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 58.336 ms | 0 - 30 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 59.892 ms | 0 - 0 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 864.502 ms | 3 - 10 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 93.796 ms | 1 - 7 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 34.275 ms | 1 - 13 MB | NPU |
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8295P | 76.101 ms | 0 - 6 MB | NPU |
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 93.796 ms | 1 - 7 MB | NPU |
License
- The license for the original implementation of Whisper-Small-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.