hello, how to export the projection onnx? about sherpa-onnx

[EmreOzkose]

This repo contains the first working version, but I have to do refactoring (adding OfflineASR, OfflineRecognizer, etc..). I am planning to do it in a few days.

[EmreOzkose]

PR is here, but not been merged yet since I didn't have time to do some changes (about testing and inference scripts). However, you can use the export script for now.

[lucasjinreal]

@EmreOzkose Hi, I only found these onnx were exported, didn't find encoder_proj.onnx or decoder_proj.onnx.

which needed by your onnx c++ inference code.

I have 2 questions:

1. the export didn't aligned with your inference code, how to resolve it?
2. you have a all_in_one model, in my opinion, this is useless, since we using encoder and decoder to inference, how didi u using it?

[lucasjinreal]

@csukuangfj Hello, can u help me out on this issue? I can not get your project run.

[csukuangfj]

What have you done and what are the error messages?

[EmreOzkose]

Hi @jinfagang , I am updating PR now. You can use export script

1. the export didn't aligned with your inference code, how to resolve it?

Export script is updated.

2. you have a all_in_one model, in my opinion, this is useless, since we using encoder and decoder to inference, how didi u using it?

Initially, the aim was to combine all parts into one .onnx like model.pt. There is a branch which uses only all-in-one.onnx to decode. It is written in Python. This repo uses Onnxruntime without dependency on Libtorch and I couldn't extract each model (encoder, decoder, etc..) internally. Hence models are given separately for now.

[lucasjinreal]

@EmreOzkose thanks. now i can get proj model as well.

the all in on infefrence, from I can see: https://github.com/EmreOzkose/sherpa/blob/887ddd0924cf5c4216a8671c39b04e8e8371356d/sherpa/bin/pruned_transducer_statelessX/offline_asr.py#L298

this still using model's decoder when greedysearch. This is not convenient on onnxruntime.

[EmreOzkose]

Offline ASR script of ONNX is https://github.com/EmreOzkose/sherpa/blob/887ddd0924cf5c4216a8671c39b04e8e8371356d/sherpa/bin/pruned_transducer_statelessX/onnx_offline_asr.py

[lucasjinreal]

Oh, I get it. Will this also port to c++ as well?

[csukuangfj]

Please use
https://github.com/k2-fsa/icefall/blob/master/egs/wenetspeech/ASR/pruned_transducer_stateless2/export.py
to export Chinese models.