FunASR-Conformer-EN: Optimized for Qualcomm Devices

FunASR Conformer-EN is a large-scale English ASR model from Alibaba DAMO Academy, trained on ~50,000 hours of English speech. It uses a 32-block Conformer encoder(512 hidden dim, 16 attention heads) with a CTC head for decoding. The model accepts raw 16kHz audio and outputs transcribed text via CTC greedy decoding.

This is based on the implementation of FunASR-Conformer-EN 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
ONNX	float	Universal	QAIRT 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

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

Model Details

Model Type: Model_use_case.speech_recognition

Model Stats:

• Input resolution: 1x160000 (10s at 16kHz)
• Model checkpoint: funasr/conformer-en
• Model size (float): ~840 MB
• Number of parameters: 220M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
FunASR-Conformer-EN	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	17.511 ms	7 - 665 MB	NPU
FunASR-Conformer-EN	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	22.422 ms	7 - 640 MB	NPU
FunASR-Conformer-EN	ONNX	float	Snapdragon® X2 Elite	23.178 ms	9 - 9 MB	NPU
FunASR-Conformer-EN	ONNX	float	Snapdragon® X Elite	44.406 ms	325 - 325 MB	NPU
FunASR-Conformer-EN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	30.573 ms	3 - 978 MB	NPU
FunASR-Conformer-EN	ONNX	float	Snapdragon® 8 Gen 1 Mobile	57.25 ms	6 - 996 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	48.247 ms	5 - 10 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	40.58 ms	0 - 387 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® QCS8450	57.25 ms	6 - 996 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	49.793 ms	7 - 11 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	44.406 ms	325 - 325 MB	NPU
FunASR-Conformer-EN	ONNX	float	Qualcomm® Dragonwing™ Q-8750	22.422 ms	7 - 640 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	18.032 ms	0 - 595 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	22.902 ms	0 - 591 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® X2 Elite	24.057 ms	0 - 0 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® X Elite	44.866 ms	0 - 0 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	30.241 ms	0 - 891 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	57.241 ms	0 - 904 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	48.488 ms	0 - 6 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	41.729 ms	1 - 7 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® SA8775P	47.827 ms	1 - 593 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® SA8650P	47.827 ms	1 - 593 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® SA8255P	47.827 ms	1 - 593 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® QCS8450	57.241 ms	0 - 904 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	49.666 ms	0 - 6 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	44.866 ms	0 - 0 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	22.902 ms	0 - 591 MB	NPU
FunASR-Conformer-EN	QNN_DLC	float	Qualcomm® SA8295P	54.375 ms	1 - 595 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	18.067 ms	3 - 624 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	22.874 ms	3 - 619 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	30.221 ms	0 - 955 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	57.359 ms	3 - 961 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	48.261 ms	3 - 335 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	41.431 ms	3 - 8 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® SA8775P	48.047 ms	3 - 621 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® SA8650P	48.047 ms	3 - 621 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® SA8255P	48.047 ms	3 - 621 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® QCS8450	57.359 ms	3 - 961 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	48.876 ms	3 - 335 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	22.874 ms	3 - 619 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® SA7255P	106.572 ms	3 - 621 MB	NPU
FunASR-Conformer-EN	TFLITE	float	Qualcomm® SA8295P	54.635 ms	3 - 614 MB	NPU

License

• The license for the original implementation of FunASR-Conformer-EN can be found here.

References

• Conformer: Convolution-augmented Transformer for Speech Recognition
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.