Nicholas Cilfone

Having similar problems with shc -rf xxxx.sh working on only the OS it was generated on... Any updates?

@gandroz Can you post your full config file you are using to generate the ~5% WER results? Thanks!!!

Thanks @gandroz! Is that the vocab here: vocabularies/librispeech_train_4_1030.subwords Edit: Based on the config it seems like you might generate one before training? Also is this just single GPU training?

Yeah just realized that you generate it based on the config options. Thanks for letting me know! I'm assuming you are doing the featurization of the WAV files in TF...

Final question I promise... It looks like you are using and tokens in SentencePiece but I'm guessing the text featurizer for the LibriSpeech transcripts doesn't have those? Or do you...

Ugh forgot that markdown will remove the notation I used... This is what I meant... It looks like you are using `` and `` tokens in SentencePiece but I'm guessing...

@gandroz any chance you can post your loss curves?

From #415 > I think we're also interested in making training completely reproducible. The problem with the current system of just recording the params, is we don't know how to...

From #415 > Something I think that would be great is some lightweight documentation showing how to integrate Replicate with configuration libraries. I've created an issue to track that. If...

Updated for CUDA 11 support which drops compute arch 30