alphacep / vosk-server

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
Apache License 2.0
882 stars 243 forks source link

"Failed to create model" despite model dir being present #174

Closed divory100 closed 2 years ago

divory100 commented 2 years ago

Hi I've been trying to use vosk-server on my raspberry pi; I've cloned the repository and downloaded a model. I extracted the model into a folder called "model", in the same directory as the websocket file i'm trying to run: asr_server.py in the websocket/ folder. However, it keeps saying "failed to create model" and is giving this output: image Any help much appreciated, Thank you very much

nshmyrev commented 2 years ago

Most likely it goes out of memory, big models are not suitable for RPI. You might try to delete rescore and rnnlm from the model, it might run then.

divory100 commented 2 years ago

Thank you, that appears to be working now :-)

nshmyrev commented 2 years ago

Same as #77