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 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 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 0.05 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.037 ms 7 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.152 ms 7 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.058 ms 0 - 6 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.076 ms 0 - 15 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.15 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.051 ms 0 - 9 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.053 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.039 ms 7 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 0.169 ms 7 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.066 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.082 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.164 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.052 ms 0 - 11 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.049 ms 0 - 10 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.139 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.149 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.054 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.309 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.069 ms 0 - 2 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.208 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.123 ms 2 - 4 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.097 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.309 ms 0 - 8 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.332 ms 0 - 5 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.048 ms 0 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.893 ms 10 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.569 ms 142 - 142 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 9.746 ms 142 - 142 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 6.478 ms 9 - 16 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.059 ms 9 - 10 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.333 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.452 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 7.137 ms 10 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 8.447 ms 75 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 13.29 ms 75 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 10.972 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 14.815 ms 9 - 11 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 16.528 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 7.583 ms 9 - 21 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 4.743 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 6.038 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.383 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 6.693 ms 2 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 23.495 ms 3 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 8.819 ms 3 - 4 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 10.731 ms 3 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.198 ms 3 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 12.137 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 23.495 ms 3 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 12.861 ms 3 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 5.317 ms 3 - 15 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.133 ms 0 - 10 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.108 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.266 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.158 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.193 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.264 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.133 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.135 ms 0 - 10 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.222 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 0.278 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.162 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.206 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.266 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.142 ms 0 - 11 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.134 ms 0 - 10 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.175 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.264 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.152 ms 0 - 7 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.485 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® SA8775P 0.329 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.233 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.228 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.485 ms 0 - 8 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.471 ms 0 - 5 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.138 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