Hugging Face's logo

qualcomm
/
Whisper-Base

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community
1

Whisper-Base: Optimized for Qualcomm Devices

HuggingFace Whisper-Base 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-Base 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-Base 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 float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit Whisper-Base 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-Base 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-base
  • Model size (decoder) (float): 187 MB
  • Model size (encoder) (float): 90.7 MB
  • Number of parameters (decoder): 48.9M
  • Number of parameters (encoder): 23.7M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.678 ms 23 - 34 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.889 ms 15 - 27 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 2.451 ms 20 - 20 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 3.673 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 3.585 ms 18 - 29 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 4.927 ms 27 - 42 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 5.669 ms 20 - 44 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.438 ms 0 - 141 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 4.927 ms 27 - 42 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 5.206 ms 20 - 43 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 3.673 ms 126 - 126 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 2.889 ms 15 - 27 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.662 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 2.835 ms 0 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 2.685 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 4.182 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 3.423 ms 8 - 16 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 4.858 ms 20 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 5.5 ms 20 - 45 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.371 ms 20 - 22 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 5.245 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 5.245 ms 20 - 29 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 4.858 ms 20 - 30 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 5.103 ms 20 - 44 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 4.182 ms 20 - 20 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 2.835 ms 0 - 12 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 5.265 ms 20 - 25 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.702 ms 20 - 30 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.828 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.825 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.856 ms 20 - 20 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 3.442 ms 1 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.819 ms 19 - 30 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.536 ms 20 - 45 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.318 ms 21 - 22 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 5.256 ms 20 - 30 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 5.256 ms 20 - 30 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.819 ms 19 - 30 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.113 ms 22 - 46 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.856 ms 20 - 20 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.828 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 5.201 ms 18 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.339 ms 38 - 45 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 23.793 ms 41 - 47 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 21.739 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 45.661 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 32.038 ms 38 - 46 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 70.929 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 53.18 ms 37 - 42 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.431 ms 7 - 56 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 70.929 ms 38 - 53 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 51.506 ms 40 - 44 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 45.661 ms 66 - 66 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 23.793 ms 41 - 47 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.37 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 24.031 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 21.985 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 46.044 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 31.98 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 70.98 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 53.035 ms 0 - 21 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.341 ms 0 - 2 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 54.916 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 54.916 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 70.98 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 51.506 ms 0 - 21 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 46.044 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 24.031 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 66.03 ms 0 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.317 ms 1 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 24.258 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 21.833 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 45.881 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 31.882 ms 1 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 70.463 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 52.995 ms 0 - 21 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 44.334 ms 1 - 7 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 54.893 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 54.893 ms 1 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 70.463 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 50.982 ms 0 - 21 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 45.881 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 24.258 ms 1 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 66.089 ms 0 - 6 MB NPU

License

  • The license for the original implementation of Whisper-Base 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