Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
FunASR-Conformer-EN

Profile Job Results

Jobs
j56o4xv05
Results Ready
Name
funasr_conformer_en
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
feats: float32[1, 167, 560]
Completion Time
10/4/2026, 7:52:19 AM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
41.4 ms
Estimated Peak Memory Usage
3 ‑ 8 MB
Compute Units
NPU
3287
StageTimeMemory
First App Load
1.02 min1,013‑1,015 MB
Subsequent App Load
535 ms329‑350 MB
Inference
41.4 ms3‑8 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device