---
library_name: pytorch
license: other
tags:
- foundation
- android
pipeline_tag: automatic-speech-recognition

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/web-assets/model_demo.png)

# 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](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/whisper_small_quantized) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://qpm.qualcomm.com/#/main/tools/details/VoiceAI_ASR) 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
| VOICE_AI | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x2_elite.zip)
| VOICE_AI | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x_elite.zip)
| VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8gen3.zip)
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8550_proxy.zip)
| VOICE_AI | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa8775p.zip)
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcm6690.zip)
| VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs9075.zip)
| VOICE_AI | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa7255p.zip)
| VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_7gen4.zip)
| VOICE_AI | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.59.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)

For more device-specific assets and performance metrics, visit **[Whisper-Small-Quantized on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small_quantized)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/whisper_small_quantized) 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](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/whisper_small_quantized) for usage instructions.

## Model Details

**Model Type:** Model_use_case.speech_recognition

**Model Stats:**
- Model checkpoint: openai/whisper-small
- Input resolution: 80x3000 (30 seconds audio)
- Max decoded sequence length: 200 tokens

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.814 ms | 33 - 33 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.187 ms | 186 - 186 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.172 ms | 38 - 50 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 10.081 ms | 38 - 52 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.914 ms | 26 - 29 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 10.081 ms | 38 - 52 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.808 ms | 24 - 57 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.187 ms | 186 - 186 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 38.564 ms | 38 - 49 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.497 ms | 28 - 36 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.7 ms | 27 - 35 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 4.7 ms | 27 - 35 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.937 ms | 23 - 33 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.497 ms | 28 - 36 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.224 ms | 30 - 30 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.3 ms | 30 - 30 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.076 ms | 30 - 39 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 12.688 ms | 20 - 29 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.823 ms | 30 - 32 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 8.822 ms | 26 - 35 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 8.822 ms | 26 - 35 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 8.822 ms | 26 - 35 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.648 ms | 25 - 60 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.3 ms | 30 - 30 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 29.771 ms | 30 - 37 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.355 ms | 28 - 34 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.637 ms | 29 - 38 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 12.688 ms | 20 - 29 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 4.637 ms | 29 - 38 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.976 ms | 24 - 34 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.355 ms | 28 - 34 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 4.247 ms | 30 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 7.475 ms | 30 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.942 ms | 23 - 31 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 12.78 ms | 21 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.919 ms | 30 - 33 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 8.956 ms | 10 - 20 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 8.956 ms | 10 - 20 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 8.956 ms | 10 - 20 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.656 ms | 25 - 60 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.475 ms | 30 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 35.073 ms | 30 - 37 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.455 ms | 28 - 34 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.648 ms | 19 - 32 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 12.78 ms | 21 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Mobile | 4.648 ms | 19 - 32 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.947 ms | 23 - 32 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.455 ms | 28 - 34 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 156.044 ms | 66 - 66 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 306.451 ms | 127 - 127 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 274.961 ms | 63 - 76 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 305.2 ms | 63 - 76 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 405.773 ms | 55 - 57 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 305.2 ms | 63 - 76 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 296.762 ms | 63 - 66 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 306.451 ms | 127 - 127 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 4499.151 ms | 2 - 13 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 489.603 ms | 31 - 42 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 229.54 ms | 63 - 77 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 229.54 ms | 63 - 77 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 174.716 ms | 64 - 73 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 489.603 ms | 31 - 42 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 156.637 ms | 0 - 0 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 304.122 ms | 0 - 0 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 268.159 ms | 1 - 8 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 518.717 ms | 1 - 9 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 366.468 ms | 1 - 32 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 315.857 ms | 0 - 9 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 315.857 ms | 0 - 9 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 315.857 ms | 0 - 9 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 297.094 ms | 0 - 29 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 304.122 ms | 0 - 0 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 3951.844 ms | 0 - 7 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 481.373 ms | 1 - 7 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 228.931 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 518.717 ms | 1 - 9 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 228.931 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 174.788 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 481.373 ms | 1 - 7 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 157.112 ms | 0 - 0 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 301.766 ms | 0 - 0 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 273.236 ms | 1 - 7 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 513.457 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 388.741 ms | 1 - 13 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 316.173 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8650P | 316.173 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8255P | 316.173 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 295.639 ms | 0 - 29 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 301.766 ms | 0 - 0 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 3948.757 ms | 1 - 13 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 480.048 ms | 1 - 7 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 231.703 ms | 1 - 13 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 513.457 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Mobile | 231.703 ms | 1 - 13 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 174.997 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 480.048 ms | 1 - 7 MB | NPU

## License
* The license for the original implementation of Whisper-Small-Quantized can be found
  [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE).

## References
* [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)
* [Source Model Implementation](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).