Josh Meyer
Josh Meyer
right now, the docs only reference training on WAV files, but we can also train on opus. similarly, we should probably rename the expected column headers in the csv data...
OOM errors happen all the time in training for newcomers and pros... we should have a simple guide on using `--reverse_{train,test,dev}` and steps to choose the right batchsize on some...
Current behavior: If a flag is duplicated at the CLI and passed to `train.py`, there is no warning or error message, and the last setting is saved. This was first...
right now we use both `progressbar2` and `tqdm`, but the latter is better maintained and the former has caused issues. We should completely replace `progressbar2` with `tqdm`
- model zoo - STT-examples - model-manager - open-speech-corpora
**Is your feature request related to a problem? Please describe.** _I have a scorer trained for language X, and it was compiled with alphabet Y. Now I have a new...
Hi Jing-Xuan, Thanks for open-sourcing this! If you include some pre-trained models, (maybe hosted on git LFS), it would be very useful for the research / open source community. -josh
Hi @jxzhanggg, I think our discussion will be interesting to others, so I'm posting this as a Github issue. If there's another place to better discuss this, let me know....
this is a confusing variable naming https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/master/pre-train/inference.py
hi @etzinis 👋 Very cool work you've got here! I'm trying to find some audio before/after samples, but can't find a link in the paper or this repo... It'd be...