---
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/main/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.

## 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 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.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/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.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/v0.51.0/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/v0.51.0/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/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/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/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.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/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.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/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.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/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_gen5.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/v0.51.0/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/v0.51.0/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/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8gen3.zip)
| VOICE_AI | w8a16 | qualcomm-qcs8275 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8275.zip)
| VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/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/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa8775p.zip)
| VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.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/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_7gen4.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/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa7255p.zip)
| VOICE_AI | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcm6690.zip)
| VOICE_AI | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs9075.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/main/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/main/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® 8 Elite Gen 5 Mobile | 3.971 ms | 30 - 41 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.806 ms | 185 - 185 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 8.145 ms | 185 - 185 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.272 ms | 33 - 40 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.295 ms | 28 - 30 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 9.066 ms | 30 - 62 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 42.773 ms | 28 - 38 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.772 ms | 19 - 32 MB | NPU
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.887 ms | 29 - 36 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.919 ms | 30 - 40 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.218 ms | 30 - 30 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.414 ms | 30 - 30 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.967 ms | 24 - 32 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 12.666 ms | 10 - 18 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.816 ms | 31 - 33 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 8.953 ms | 26 - 35 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.656 ms | 25 - 60 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 29.637 ms | 30 - 37 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 12.666 ms | 10 - 18 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.62 ms | 22 - 31 MB | NPU
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.449 ms | 29 - 36 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.902 ms | 30 - 40 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 4.247 ms | 30 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 7.358 ms | 30 - 30 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.003 ms | 30 - 39 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS8275 (Proxy) | 12.775 ms | 30 - 39 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.793 ms | 30 - 32 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 8.997 ms | 29 - 38 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® QCS9075 | 8.655 ms | 25 - 60 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® QCM6690 | 30.457 ms | 28 - 34 MB | NPU
| decoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 12.775 ms | 30 - 39 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.612 ms | 21 - 35 MB | NPU
| decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.479 ms | 30 - 37 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 176.433 ms | 63 - 73 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 155.344 ms | 127 - 127 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 266.244 ms | 127 - 127 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 248.059 ms | 63 - 70 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 333.657 ms | 0 - 129 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 256.887 ms | 63 - 66 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 4336.016 ms | 2 - 13 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 196.563 ms | 63 - 75 MB | NPU
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 457.053 ms | 57 - 67 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 188.87 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 156.171 ms | 0 - 0 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 302.188 ms | 0 - 0 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.617 ms | 1 - 8 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 525.284 ms | 0 - 8 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 392.632 ms | 1 - 33 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 315.833 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 297.123 ms | 0 - 29 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 4189.979 ms | 1 - 12 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 525.284 ms | 0 - 8 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 222.474 ms | 1 - 10 MB | NPU
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 482.192 ms | 0 - 7 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 191.472 ms | 1 - 10 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 153.678 ms | 0 - 0 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 303.085 ms | 0 - 0 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.398 ms | 1 - 8 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS8275 (Proxy) | 512.111 ms | 1 - 9 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | 376.546 ms | 1 - 26 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 316.614 ms | 0 - 9 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® QCS9075 | 296.165 ms | 1 - 29 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® QCM6690 | 4457.874 ms | 1 - 12 MB | NPU
| encoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 512.111 ms | 1 - 9 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 226.069 ms | 1 - 9 MB | NPU
| encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 480.523 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).