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 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.25.0 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 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 Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy 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
QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 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® 8 Elite Gen 5 Mobile 0.049 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.063 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.074 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.051 ms 0 - 12 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.151 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 0.051 ms 0 - 12 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.051 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.058 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.073 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.167 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.051 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8750 0.051 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.045 ms 0 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.123 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.139 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.058 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 0.296 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.063 ms 0 - 1 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.207 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 0.207 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 0.207 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.045 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.122 ms 0 - 2 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.099 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.296 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.322 ms 0 - 6 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 0.045 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 0.139 ms 0 - 0 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.859 ms 10 - 19 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 6.611 ms 9 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.014 ms 0 - 159 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.449 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.368 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 5.449 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 7.332 ms 10 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 10.93 ms 9 - 16 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 15.329 ms 0 - 79 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 16.53 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 7.686 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8750 7.686 ms 9 - 17 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 4.763 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 5.895 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.476 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 6.548 ms 2 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 23.382 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 9.056 ms 3 - 4 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 10.578 ms 3 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 10.578 ms 3 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 10.578 ms 3 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 5.442 ms 3 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.109 ms 3 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 12.14 ms 2 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 23.382 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 13.061 ms 3 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 5.442 ms 3 - 15 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 9.476 ms 3 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.128 ms 0 - 9 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.163 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.19 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.137 ms 0 - 11 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.276 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 0.137 ms 0 - 11 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.136 ms 0 - 10 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.174 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.203 ms 0 - 9 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.312 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.136 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8750 0.136 ms 0 - 7 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 Snapdragon® X2 Elite 0.177 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 0.16 ms 0 - 7 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8275 0.491 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.184 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.318 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8650P 0.318 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8255P 0.318 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.138 ms 0 - 13 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.236 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.229 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.491 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.453 ms 0 - 6 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8750 0.138 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