Closed itzsimpl closed 2 years ago
The validation step isn't exactly necessary, try to see if export works without it.
I first tried just exporting, since that didn't work I tried also the validation step in hope of getting a little bit more information.
In both cases conversion fails with [W] 'Shape tensor cast elision' routine failed with: None
. In addition validation fails with Condition for key 'min_nemo_version' (1.3 <built-in function eq> 1.1) is not fulfilled
, regardless the fact that I was using the nemo:22.01
container (hence nemo:1.7.1
) or an upgraded version from GitHub (nemo:1.9.0rc0
). Checking the manifest of stt_en_conformer_ctc_large_1.6.0
for the presence of nemo_version
reveals it is not present. However even if starting off of stt_en_conformer_ctc_large_1.6.0
I create a new model, thus add nemo_version: 1.7.1
to the manifest, the errors are always the same.
FWW. Browsing for Warning: Constant folding - Only steps=1 can be constant
leads me to https://github.com/pytorch/pytorch/issues/73843, but I'm clueless in how to test if this is at all related.
That is a warning not an error for constant folding. If should bare no impact on the final model export
The validation check is mostly not used even by Riva devs, since the check is more strict than necessary.
@titu1994 my bad, sorry for that. It seems that everything works as it should. The conversion is successful, and I can successfully load the model on Riva 2.0.0, it is just that the initial conversion ends with a bit "misleading" warning "... routine failed with: None", which is not present under Riva 1.10.0-beta.
Start off with
nemo:22.01
container, installriva_quickstart_v2.0.0
(riva_api
andnemo2riva
), downloadstt_en_conformer_ctc_large_1.6.0
from ngc and unzip it.Running
nemo2riva --out stt_en_conformer_ctc_large.riva stt_en_conformer_ctc_large.nemo
gives the following outputRunning
nemo2riva --validate stt_en_conformer_ctc_large.nemo
gives the same output, but at the end appends the following linesUsing
reinstall.sh
to installnemo:1.9.0rc0
makes no difference.