Pre-trained models about svoice HOT 10 OPEN

Hi @jainal09,
We are working on it! :) I believe we will be able to upload some models soon.
Will update of course :)

from svoice.

I dont understand why is this the problem. Because I have seen Nvidia open sourcing their Nemo asr model that was trained on WSJ dataset. - https://ngc.nvidia.com/catalog/models/nvidia:wsj_quartznet_15x5

from svoice.

@adiyoss Is there any update as to when the pre trained model on librispeech will be available?
Edit:
I was wondering if you could please provide some information about the resources that were required to train the model to completion. Figure 4 in the paper shows the training over 60 hours but does not mention the hardware used. Was this on a single gpu or on hundreds of them?

from svoice.

@adiyoss Hi, thanks for the repo. Is there any update on pretrained models?

from svoice.

Great job. Expect pre-trained models.

from svoice.

Hi @rafaelvalle,
Unfortunately, since the model was trained using the WSJ dataset, which is not publicly available, we can not legally release pre-trained models.
However, if you have access to this dataset you can train it on your own (all relevant details are in the repo). Another option is to train using the librimix dataset (based on librispeech).

from svoice.

If anyone does train a model on any other dataset PLEASE do upload it and help us out, thanks

from svoice.

Hi @jainal09,
We are working on it! :) I believe we will be able to upload some models soon.
Will update of course :)

Hello. Plan to train librimix dataset (based on librispeech) ?

from svoice.

Hello, I tried to run the voice separation using the trained models available at https://ngc.nvidia.com/catalog/models/nvidia:wsj_quartznet_15x5 but got the following error
in deserialize_model klass = package['class'] KeyError: 'class'
Do you know how to fix this error and run voice separation on a custom .wav file?

from svoice.

A pretrained model would be great :)

from svoice.