Hugging Face's logo

qualcomm
/
Zipformer

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Zipformer: Optimized for Qualcomm Devices

Zipformer streaming ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text streamingly. This model is based on the transformer architecture and has been optimized for edge inference by replacing 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 audios. Time to the first token is the encoder's latency, while time to each additional token is joiner's latency, where we assume a max decoded length specified below.

This is based on the implementation of Zipformer 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
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS9075 QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Zipformer 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 Zipformer on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.speech_recognition

Model Stats:

  • Model checkpoint: pfluo/k2fsa-zipformer-chinese-english-mixed
  • Input resolution: 80x71 (0.71 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Number of parameters (encoder): 63.2M
  • Model size (encoder) (float): 242 MB
  • Number of parameters (decoder): 3.47M
  • Model size (decoder) (float): 13.2 MB
  • Number of parameters (joiner): 3.21M
  • Model size (joiner) (float): 12.2 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.035 ms 1 - 1 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.041 ms 7 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.063 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 0.107 ms 0 - 9 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.074 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 0.107 ms 0 - 9 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.051 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.149 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 0.05 ms 0 - 11 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 0.05 ms 0 - 11 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS7181 0.041 ms 7 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.135 ms 1 - 1 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.149 ms 1 - 1 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.055 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 0.098 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 0.3 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.075 ms 0 - 1 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 0.098 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.051 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.3 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.121 ms 0 - 2 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 0.044 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.328 ms 0 - 6 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 0.044 ms 0 - 13 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 0.149 ms 1 - 1 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.769 ms 10 - 10 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 9.383 ms 142 - 142 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 6.644 ms 9 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 12.234 ms 9 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.048 ms 10 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 12.234 ms 9 - 23 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.888 ms 7 - 16 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.238 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 5.405 ms 10 - 21 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 5.405 ms 10 - 21 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS7181 9.383 ms 142 - 142 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 6.241 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.62 ms 2 - 2 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 6.657 ms 2 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 12.032 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 23.527 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 8.895 ms 3 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 12.032 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 4.828 ms 3 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 23.527 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.116 ms 3 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 5.416 ms 3 - 16 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 13.18 ms 3 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 5.416 ms 3 - 16 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 9.62 ms 2 - 2 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.081 ms 1 - 1 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.141 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.156 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 0.251 ms 0 - 14 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.192 ms 0 - 9 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 0.251 ms 0 - 14 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.134 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.271 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 0.137 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 0.137 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS7181 0.141 ms 6 - 6 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.179 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.249 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.151 ms 0 - 8 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 0.229 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8275 0.5 ms 0 - 8 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.187 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8450 0.229 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.129 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.5 ms 0 - 8 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.244 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 0.136 ms 0 - 13 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.452 ms 0 - 5 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8750 0.136 ms 0 - 13 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS7181 0.249 ms 0 - 0 MB NPU

License

  • The license for the original implementation of Zipformer 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