David Zurow

@bluecamel Oops, actually I think that is leftover and `2020-11-28` would be fine. I pushed an update. Thanks for any help!

FYI, I decided to try to treat the docker image as evergreen, and keep the things liable to change a lot like scripts in the git repo instead.

Thanks for the encouragement! The current published models were trained using my fork of Zamia, which has diverged significantly from upstream, and which has been too messy with too many...

I'm working on simplifying and documenting how to perform fine tuning. I would say to use https://github.com/daanzu/kaldi-active-grammar/releases/download/v1.4.0/kaldi_model_daanzu_20200328_1ep-mediumlm.zip I've had more success with the procedure in `egs/aishell2/s5/local/nnet3/tuning/finetune_tdnn_1a.sh` adapted for chain.

I am planning on doing much more experimentation on this soon, but I think I had most success with parameters like this: ``` num_epochs=5 initial_effective_lrate=.00025 final_effective_lrate=.000025 minibatch_size=1024 ```

Great! Thanks for the WER% info.

@vasudev-hv This is a nnet3 chain model, not tri3. The other files can be generated from the ones included in the download.

@JohnDoe02 Wow, great detailed write up! Thanks for posting it. As stated earlier, I had more success adapting the `aishell2` finetuning script than `run_tdnn_wsj_rm_1c`, although it has been a while...

https://gist.github.com/daanzu/d29e18abb9e21ccf1cddc8c3e28054ff It's not pretty, but maybe it can be of use until I have something better. Regarding training files length, including a some amount of prose dictation of reasonable length...

It's been a while since I started experimenting, and I can't recall exactly how I ended up with this. I think the `chain.alignment-subsampling-factor` is because I generate the alignments with...