21–22 of 22 posts
Earlier quoted context omitted.
Then it's unfortunate Apple decided to integrate AMD and Intel cards into MacBook Pro's instead of Nvidia. Many ML researchers probably use MBP's but can't leverage acceleration.
You wouldn't wanna run long-running models that take days to train on your laptop anyway.
It's a reasonable use case.
This is very good - I've never seen a RNN-for-speech-in-Tensorflow model before. Note, though that the real problem here is the lack of training data. In a recent podcast I heard that the Baidu speech recognition team uses "small models" of 10,000 hours of speech. I forget how big the production quality models were, but it was at least 5 times that. This model uses ~1500 hours[1]. It's very impressive it does as well…
Mozilla Deepspeech has been around for a while ( https://github.com/mozilla/DeepSpeech ). In fact, this code looks like it heavily copied from there (see attribution notices in comments). Their examples use much less data, just 5 utterances from the Librispeech training set. Which is perfectly fine for a tutorial, since training on 1500h worth of speech data takes from several days to multiple weeks, depending on you…