k2-fsa / sherpa

Speech-to-text server framework with next-gen Kaldi
https://k2-fsa.github.io/sherpa
Apache License 2.0
532 stars 107 forks source link

Any plan for use multi-thread WASM in sherpa-onnx as nodejs library, I need to use realtime recognition on Raspberry Pi 4B #563

Open jackwei86 opened 6 months ago

jackwei86 commented 6 months ago

Current Model used in RaspberryPi 4B is: sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20,which is not a small model. The

recongition speed is too slow. I have to use a smaller model to solve the delay as the system is running in realtime.