Hugging Face's logo

qualcomm
/
Whisper-Small

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Small: Optimized for Qualcomm Devices

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 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.

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
QNN_CONTEXT_BINARY float qualcomm_qcs8450_proxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_qcs8550_proxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_qcs9075 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa7255p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa8295p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_sa8775p QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8_elite_for_galaxy QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8_elite_gen5 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_8gen3 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_x2_elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY float qualcomm_snapdragon_x_elite QAIRT 2.43 Download

For more device-specific assets and performance metrics, visit Whisper-Small 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 on GitHub 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
  • Number of parameters (encoder): 102M
  • Model size (encoder) (float): 391 MB
  • Number of parameters (decoder): 139M
  • Model size (decoder) (float): 533 MB

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 Mobile 7.222 ms 75 - 84 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 6.095 ms 286 - 286 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 10.441 ms 285 - 285 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 9.84 ms 73 - 85 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 12.133 ms 61 - 64 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 13.335 ms 60 - 122 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 8.401 ms 58 - 68 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 7.266 ms 60 - 70 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 6.525 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.745 ms 60 - 60 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 9.819 ms 37 - 45 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 19.804 ms 31 - 40 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 12.176 ms 55 - 65 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 13.725 ms 60 - 69 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 13.427 ms 60 - 128 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 17.396 ms 39 - 49 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 19.804 ms 31 - 40 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 15.117 ms 46 - 51 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 8.3 ms 8 - 22 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 46.51 ms 89 - 99 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 47.572 ms 202 - 202 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 115.428 ms 201 - 201 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 82.255 ms 129 - 138 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 112.855 ms 0 - 225 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 137.101 ms 126 - 130 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 59.055 ms 127 - 139 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 45.088 ms 1 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 47.766 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 114.908 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 85.441 ms 1 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 405.533 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 112.557 ms 0 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 136.563 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 136.464 ms 0 - 55 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 281.823 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 405.533 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 205.937 ms 1 - 6 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 60.399 ms 1 - 14 MB NPU

License

  • The license for the original implementation of Whisper-Small 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