Hugging Face's logo

qualcomm
/
Zipformer

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community
Zipformer / README.md
qaihm-bot's picture
qaihm-bot
v0.51.0
00b6457 verified
preview code
|
raw
history blame contribute delete
18.2 kB
metadata 
library_name: pytorch
license: other
tags:
  - foundation
  - android
pipeline_tag: automatic-speech-recognition

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 0.052 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.035 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 0.059 ms 0 - 7 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.065 ms 0 - 9 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.189 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.051 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.054 ms 0 - 10 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.041 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) 0.078 ms 0 - 8 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.166 ms 0 - 3 MB NPU
decoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.053 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.045 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.13 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.152 ms 0 - 0 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.056 ms 0 - 7 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.311 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.074 ms 0 - 1 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.206 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.135 ms 0 - 2 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.098 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.311 ms 0 - 9 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.316 ms 0 - 5 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.05 ms 0 - 13 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.886 ms 10 - 20 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 5.407 ms 142 - 142 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 9.732 ms 142 - 142 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 6.615 ms 9 - 17 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 9.107 ms 10 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 10.393 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.475 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 8.359 ms 75 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 13.525 ms 75 - 75 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 11.201 ms 11 - 18 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 15.991 ms 9 - 10 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 16.661 ms 8 - 12 MB NPU
encoder PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 7.587 ms 9 - 21 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 4.781 ms 3 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 6.092 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 9.335 ms 3 - 3 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 6.626 ms 2 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 23.469 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 8.905 ms 3 - 5 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 10.702 ms 3 - 11 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 10.225 ms 3 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 12.035 ms 3 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 23.469 ms 3 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 12.991 ms 3 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 5.365 ms 3 - 15 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.136 ms 0 - 10 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 0.092 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 0.251 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 0.153 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 0.188 ms 0 - 9 MB NPU
joiner PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 0.271 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.136 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite Gen 5 Mobile 0.137 ms 0 - 10 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X2 Elite 0.085 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® X Elite 0.266 ms 6 - 6 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Gen 3 Mobile 0.158 ms 0 - 7 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS8550 (Proxy) 0.203 ms 0 - 8 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Qualcomm® QCS9075 0.278 ms 0 - 3 MB NPU
joiner PRECOMPILED_QNN_ONNX mixed Snapdragon® 8 Elite For Galaxy Mobile 0.136 ms 0 - 7 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 0.132 ms 0 - 10 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 0.176 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® X Elite 0.245 ms 0 - 0 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 0.161 ms 0 - 7 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 0.474 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 0.179 ms 0 - 1 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8775P 0.316 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS9075 0.235 ms 0 - 2 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 0.228 ms 0 - 8 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA7255P 0.474 ms 0 - 9 MB NPU
joiner QNN_CONTEXT_BINARY float Qualcomm® SA8295P 0.457 ms 0 - 5 MB NPU
joiner QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 0.135 ms 0 - 8 MB NPU

License

  • The license for the original implementation of Zipformer can be found here.

References

Community