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® 8 Elite Gen 5 Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.1 Download
PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 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® QCS9075 QAIRT 2.43 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Snapdragon® X2 Elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Snapdragon® X Elite QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Snapdragon® 8 Gen 3 Mobile QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Qualcomm® QCS8550 (Proxy) QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Qualcomm® SA8775P QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Qualcomm® SA7255P QAIRT 2.43 Download
QNN_CONTEXT_BINARY mixed Qualcomm® QCS9075 QAIRT 2.43 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 (ZipformerEncoder): 63.2M
  • Model size (ZipformerEncoder) (float): 242 MB
  • Number of parameters (ZipformerDecoder): 3.47M
  • Model size (ZipformerDecoder) (float): 13.2 MB
  • Number of parameters (ZipformerJoiner): 3.21M
  • Model size (ZipformerJoiner) (float): 12.2 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
ZipformerDecoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.051 ms 0 - 10 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.033 ms 7 - 7 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.152 ms 7 - 7 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.063 ms 0 - 7 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.074 ms 0 - 9 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.188 ms 0 - 3 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.052 ms 0 - 12 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.046 ms 0 - 10 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.043 ms 7 - 7 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 0.163 ms 7 - 7 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.065 ms 0 - 6 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.079 ms 0 - 8 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.158 ms 0 - 3 MB NPU
ZipformerDecoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.054 ms 0 - 7 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.046 ms 0 - 9 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.132 ms 0 - 0 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.164 ms 0 - 0 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.058 ms 0 - 7 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.309 ms 0 - 8 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.069 ms 0 - 5 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.217 ms 0 - 5 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.125 ms 0 - 2 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.096 ms 0 - 8 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.309 ms 0 - 8 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.317 ms 0 - 5 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.044 ms 0 - 9 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite Gen 5 Mobile 0.05 ms 0 - 9 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Snapdragon® X2 Elite 0.131 ms 0 - 0 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Snapdragon® X Elite 0.154 ms 0 - 0 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Gen 3 Mobile 0.065 ms 0 - 6 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS8275 (Proxy) 0.335 ms 0 - 8 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS8550 (Proxy) 0.071 ms 0 - 1 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Qualcomm® SA8775P 0.225 ms 0 - 5 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS9075 0.133 ms 0 - 2 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Qualcomm® SA7255P 0.335 ms 0 - 8 MB NPU
ZipformerDecoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite For Galaxy Mobile 0.051 ms 0 - 9 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.898 ms 10 - 19 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.445 ms 142 - 142 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 9.694 ms 142 - 142 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 6.688 ms 9 - 17 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.047 ms 9 - 11 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.359 ms 8 - 12 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.682 ms 9 - 20 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 7.191 ms 10 - 20 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 8.406 ms 75 - 75 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 13.524 ms 75 - 75 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 10.765 ms 9 - 16 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 14.146 ms 10 - 12 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 16.57 ms 8 - 12 MB NPU
ZipformerEncoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 7.554 ms 9 - 16 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 4.758 ms 3 - 13 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 6.232 ms 3 - 3 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.529 ms 3 - 3 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 6.617 ms 2 - 10 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 23.781 ms 3 - 10 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 8.925 ms 3 - 4 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 10.93 ms 3 - 11 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.221 ms 3 - 7 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 12.576 ms 2 - 12 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 23.781 ms 3 - 10 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 13.295 ms 1 - 6 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 5.388 ms 3 - 16 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite Gen 5 Mobile 7.09 ms 3 - 13 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Snapdragon® X2 Elite 8.811 ms 3 - 3 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Snapdragon® X Elite 13.197 ms 3 - 3 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Gen 3 Mobile 10.533 ms 2 - 12 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS8275 (Proxy) 24.95 ms 3 - 11 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS8550 (Proxy) 14.526 ms 3 - 5 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Qualcomm® SA8775P 16.083 ms 3 - 12 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Qualcomm® QCS9075 15.897 ms 3 - 8 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Qualcomm® SA7255P 24.95 ms 3 - 11 MB NPU
ZipformerEncoder QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite For Galaxy Mobile 7.542 ms 3 - 15 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.134 ms 0 - 10 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.082 ms 6 - 6 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.263 ms 6 - 6 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.154 ms 0 - 7 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.191 ms 0 - 8 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.27 ms 0 - 3 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.134 ms 0 - 12 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.137 ms 0 - 10 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.088 ms 6 - 6 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 0.278 ms 6 - 6 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.159 ms 0 - 7 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.204 ms 0 - 8 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.272 ms 0 - 3 MB NPU
ZipformerJoiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.14 ms 0 - 7 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.13 ms 0 - 10 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.176 ms 0 - 0 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.254 ms 0 - 0 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.143 ms 0 - 7 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.48 ms 0 - 8 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.187 ms 0 - 1 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.917 ms 0 - 8 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.235 ms 0 - 2 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.235 ms 0 - 9 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.48 ms 0 - 8 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.466 ms 0 - 5 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.147 ms 0 - 13 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite Gen 5 Mobile 0.132 ms 0 - 10 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Snapdragon® X2 Elite 0.179 ms 0 - 0 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Snapdragon® X Elite 0.261 ms 0 - 0 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Snapdragon® 8 Gen 3 Mobile 0.157 ms 0 - 7 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Qualcomm® QCS8275 (Proxy) 0.461 ms 0 - 9 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Qualcomm® QCS8550 (Proxy) 0.199 ms 0 - 2 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Qualcomm® SA8775P 0.343 ms 0 - 5 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Qualcomm® QCS9075 0.249 ms 0 - 2 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Qualcomm® SA7255P 0.461 ms 0 - 9 MB NPU
ZipformerJoiner QNN_CONTEXT_BINARY mixed Snapdragon® 8 Elite For Galaxy Mobile 0.148 ms 0 - 13 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