DeepSpeech model training accuracy

[parthv21 (Lumens)]

I can’t see the training accuracy for https://github.com/mozilla/DeepSpeech. All I see is the loss.

[baconator]

They have it on the release notes usually.

[lissyx ((slow to reply) [NOT PROVIDING SUPPORT])]

Train more: test set will be executed at the end.

[lissyx ((slow to reply) [NOT PROVIDING SUPPORT])]

@parthv21

But it crashed before I could see accuracy. Is it supposed to output accuracy after training?

As said, and documented, test set is run after full training.

[lissyx ((slow to reply) [NOT PROVIDING SUPPORT])]

Please follow the forum guidelines and avoid sharing such material as screenshots.

[lissyx ((slow to reply) [NOT PROVIDING SUPPORT])]

@parthv21

is not listed at the end of the training?

It is, see the “WER”.

[parthv21 (Lumens)]

So does that mean there is 100% accuracy?

[othiele (Olaf Thiele)]

We are happy to help, but you have given us next to zero information. Try training a really small dataset completely without error and start from there. If you need more:

[READ FIRST] What and how to report if you need support

We are happy for every new user of DeepSpeech. As it is under active development, stuff changes quickly and you might have problems running it. We are here to help and might point to this thread if needed Please do the following before posting: Search this forum or Google for your problem Read the documentation for your version here Check the new Playbook on how to use DeepSpeech Check Github issues for more technical problems If you still struggle, feel free to open a new t…

[lissyx ((slow to reply) [NOT PROVIDING SUPPORT])]

You need to do your homework and search for Word Error Rate.