Hugging Face's logo

qualcomm
/
Whisper-Small-Quantized

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
Community

Whisper-Small-Quantized: Optimized for Mobile Deployment

Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace

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 model is an implementation of Whisper-Small-Quantized found here.

This repository provides scripts to run Whisper-Small-Quantized on Qualcomm® devices. More details on model performance across various devices, can be found here.

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
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
WhisperSmallEncoderQuantizable w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_CONTEXT_BINARY 128.052 ms 1 - 10 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_CONTEXT_BINARY 112.608 ms 1 - 21 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_CONTEXT_BINARY 62.325 ms 1 - 3 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) PRECOMPILED_QNN_ONNX 62.524 ms 0 - 115 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 58.95 ms 1 - 10 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_CONTEXT_BINARY 613.165 ms 1 - 13 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) PRECOMPILED_QNN_ONNX 612.722 ms 29 - 40 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 SA7255P ADP Qualcomm® SA7255P QNN_CONTEXT_BINARY 128.052 ms 1 - 10 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_CONTEXT_BINARY 61.478 ms 0 - 3 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 SA8295P ADP Qualcomm® SA8295P QNN_CONTEXT_BINARY 80.04 ms 1 - 17 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_CONTEXT_BINARY 62.303 ms 1 - 3 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 SA8775P ADP Qualcomm® SA8775P QNN_CONTEXT_BINARY 58.95 ms 1 - 10 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 43.635 ms 1 - 19 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 44.395 ms 56 - 75 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 35.072 ms 1 - 14 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 36.148 ms 54 - 67 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_CONTEXT_BINARY 191.005 ms 1 - 15 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile PRECOMPILED_QNN_ONNX 184.911 ms 54 - 63 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 28.292 ms 0 - 12 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 28.678 ms 61 - 72 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 61.61 ms 0 - 0 MB NPU Use Export Script
WhisperSmallEncoderQuantizable w8a16 Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 61.896 ms 108 - 108 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_CONTEXT_BINARY 13.422 ms 27 - 36 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_CONTEXT_BINARY 11.469 ms 29 - 46 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_CONTEXT_BINARY 8.49 ms 30 - 33 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) PRECOMPILED_QNN_ONNX 8.83 ms 30 - 32 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_CONTEXT_BINARY 9.441 ms 24 - 34 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_CONTEXT_BINARY 32.888 ms 27 - 38 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) PRECOMPILED_QNN_ONNX 34.862 ms 37 - 49 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 SA7255P ADP Qualcomm® SA7255P QNN_CONTEXT_BINARY 13.422 ms 27 - 36 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_CONTEXT_BINARY 8.26 ms 35 - 37 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 SA8295P ADP Qualcomm® SA8295P QNN_CONTEXT_BINARY 10.538 ms 30 - 46 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_CONTEXT_BINARY 8.403 ms 26 - 28 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 SA8775P ADP Qualcomm® SA8775P QNN_CONTEXT_BINARY 9.441 ms 24 - 34 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_CONTEXT_BINARY 6.394 ms 30 - 48 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile PRECOMPILED_QNN_ONNX 6.854 ms 38 - 57 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_CONTEXT_BINARY 4.825 ms 28 - 42 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile PRECOMPILED_QNN_ONNX 5.182 ms 26 - 42 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile QNN_CONTEXT_BINARY 11.331 ms 30 - 45 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon 7 Gen 5 QRD Snapdragon® 7 Gen 5 Mobile PRECOMPILED_QNN_ONNX 11.918 ms 38 - 50 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_CONTEXT_BINARY 4.047 ms 28 - 40 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile PRECOMPILED_QNN_ONNX 4.395 ms 37 - 48 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_CONTEXT_BINARY 7.733 ms 30 - 30 MB NPU Use Export Script
WhisperSmallDecoderQuantizable w8a16 Snapdragon X Elite CRD Snapdragon® X Elite PRECOMPILED_QNN_ONNX 7.756 ms 186 - 186 MB NPU Use Export Script

Installation

Install the package via pip:

pip install "qai-hub-models[whisper-small-quantized]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.whisper_small_quantized.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.whisper_small_quantized.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.whisper_small_quantized.export

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Whisper-Small-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of Whisper-Small-Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support