collabora / WhisperLive

A nearly-live implementation of OpenAI's Whisper.
MIT License
2.09k stars 283 forks source link

TensorRT backend gives no output #261

Closed jasonngap1 closed 2 months ago

jasonngap1 commented 3 months ago

Hi, I have built a TensoRT engine and tried running the command:

python3 run_server.py -p 9090 -b tensorrt -trt {path_to_engine}

but the only output that I have received is the below:

INFO:root:Custom model option was provided. Switching to single model mode.

Is there something that I am doing wrong? I built the model using the repo here: https://github.com/k2-fsa/sherpa/tree/master/triton/whisper