search

k2-fsa / sherpa

Speech-to-text server framework with next-gen Kaldi
https://k2-fsa.github.io/sherpa
Apache License 2.0
483 stars 97 forks source link

Triton_server #419

Open alidabaghi123 opened 1 year ago

alidabaghi123 commented 1 year ago

Hello. I'm trying to deploy my trained streaming model, which I exported to the ONNX format, on TRTorch, and I'm encountering the following error. Screenshot from 2023-06-28 15-44-28

joazoa commented 1 year ago

The error should be a bit above what you copy pasted.

yuekaizhang commented 1 year ago

Have you tried our official recipe first? https://github.com/k2-fsa/sherpa/blob/master/triton/scripts/build_librispeech_pruned_transducer_stateless3_streaming.sh and https://github.com/k2-fsa/sherpa/blob/master/triton/scripts/build_wenetspeech_pruned_transducer_stateless5_streaming.sh. We currently support reworked conformer streaming ASR for en and zh.

alidabaghi123 commented 1 year ago

thank you for answering, i haved tried for zipformer_streaming. do you support this?

yuekaizhang commented 1 year ago

Not yet. We will try to support this in a month. Or you're welcome to contribute a script or a model_repo to support it e.g. build_librispeech_zipformer2_streaming.sh

alidabaghi123 commented 1 year ago

thank you. sorry i didnt have work with triton.