Testing pre trained model

[JRMeyer]

>>> amir.kovaci
[September 20, 2019, 9:13am]

Hi, I have downloaded the pre-trained model: slash
wget
https://github.com/mozilla/DeepSpeech/releases/download/v0.5.1/deepspeech-0.5.1-models.tar.gz slash
tar xvfz deepspeech-0.5.1-models.tar.gz

But when we test it (non-native English speaker), a lot of words get
mismatched and they seem not to be in english? Is it supposed to
recognize english text correctly of non native speakers?

thanks

[This is an archived TTS discussion thread from discourse.mozilla.org/t/testing-pre-trained-model]

[JRMeyer]

>>> lissyx
[September 20, 2019, 11:23am]



> Is it supposed to recognize english text correctly of non native
> speakers?

It's not that it is supposed, it's just that for now, the training
dataset is mainly from native speakers, so the model has more
difficulties with non native speakers. More contribution to Common Voice
in English from non native speakers would help improve that.

[Archived Post]

[JRMeyer]

>>> albanmurturi
[September 20, 2019, 12:31pm]

when downloading the trained
model, the size is around 1.8 GB, is this trained model from this
dataset which is 30 GB https://voice.mozilla.org/en/datasets

[Archived Post]

[JRMeyer]

>>> lissyx
[September 20, 2019, 12:32pm]



when downloading the trained
> model, the size is around 1.8 GB, is this trained model from this
> dataset which is 30 GB https://voice.mozilla.org/en/datasets

I don't get your point. v0.5.1 was not trained against Common Voice,
because of a mistake, but v0.4.1 was and next v0.6 will be.

[Archived Post]

[JRMeyer]

>>> dabinat
[September 21, 2019, 1:30am]

The size of the model file is dependent upon the parameters chosen, not
the size of the dataset, and does not contain raw sound data. So a model
trained on 30 GBs of data doesn't necessarily mean the model will be 30
GBs - it will most likely be a tiny fraction of that.

(In fact, if you look at the size of the files in the download, the
model is only around 190 MB and most of the size is taken up by the
language model.)

[Archived Post]