Tatiana Likhomanenko

Thanks for reporting this issue. The commit you pointed fixed the problem for standard ctc model decoding when we train it with surround. We will investigate how the inference should...

cc @vineelpratap @xuqiantong

Hi @phamvandan Could you give details how you changes the tokens set and how the lexicon is created? Also additional note: When you fork - you use the same network,...

One of the solutions https://github.com/facebookresearch/wav2letter/issues/829. Let me know if it is not clear. Here is also recent snapshot on doing similar thing https://github.com/facebookresearch/flashlight/blob/master/flashlight/app/asr/tutorial/FinetuneCTC.cpp#L254-L270 but you need to exclude last index...

Yes. But this should be simple. Let me know if you need help in rebuild.

You need to follow installation either with docker image https://github.com/facebookresearch/flashlight/blob/master/.docker/Dockerfile-CUDA or from source https://github.com/facebookresearch/flashlight#building-from-source (you modify Train.cpp and then rerun `make` command).

Could you run without distributed training? Do you have all 1-9 epochs passed fine?

Can you confirm that if you rerun training from epoch 1 it is still working?

Seems you didn't install all dependencies we have, so please follow all instructions on dependencies installation. https://github.com/flashlight/flashlight#dependencies

Could you report exact commands you run, details on your platform and the way you installing (building from source, vcpkg, docker, which backend)