DeepSpeech 0.6

#1

Post by pionerkotik » Thu, Dec 05, 2019, 9:29 AM UTC

Re: DeepSpeech 0.6

#2

Post by tobylane » Thu, Dec 05, 2019, 9:48 AM UTC

I'm starting to look into the MycroftAI. It sounds like with this release I could use Mycroft+DeepSpeech on a new RaspberryPi for a completely offline smart speaker, do I understand that right?

Re: DeepSpeech 0.6

#3

Post by zitterbewegung » Thu, Dec 05, 2019, 9:51 AM UTC

tobylane wrote: post #2

I'm starting to look into the MycroftAI. It sounds like with this release I could use Mycroft+DeepSpeech on a new RaspberryPi for a completely offline smart speaker, do I understand that right?

Yes, you are correct tensorflow lite can be done on the raspberry pi. https://www.tensorflow.org/lite/guide/build_rpi

Re: DeepSpeech 0.6

#4

Post by est31 » Thu, Dec 05, 2019, 9:57 AM UTC

Congrats to the team on the new release! Following their progress since a while. It's an important project, and I'm very happy about the size reductions while they still delivered a WER improvement over the last release. Amazing!

Re: DeepSpeech 0.6

#5

Post by detaro » Thu, Dec 05, 2019, 10:00 AM UTC

> It achieves a 7.5% word error rate on the LibriSpeech test clean benchmark

Anyone have a comparison for how good/bad that is compared to other solutions, and what it means for practical usage, if that can be guessed at from a single number?

Re: DeepSpeech 0.6

#6

Post by Traktor » Thu, Dec 05, 2019, 10:15 AM UTC

detaro wrote: post #5

> It achieves a 7.5% word error rate on the LibriSpeech test clean benchmark Anyone have a comparison for how good/bad that is compared to other solutions, and what it means for practical usage, if that can be guessed at from a single number?

You can find a leaderboard here: https://paperswithcode.com/sota/speech-recognition-on-libris...

It seems like sota is 2.20% word error rate

Re: DeepSpeech 0.6

#7

Post by bayesian_horse » Thu, Dec 05, 2019, 10:20 AM UTC

I wonder if it is any good at out-of-vocabulary words? Is it hard to teach it new things like medical terms and such?

Re: DeepSpeech 0.6

#8

Post by est31 » Thu, Dec 05, 2019, 10:21 AM UTC

detaro wrote: post #5

> It achieves a 7.5% word error rate on the LibriSpeech test clean benchmark Anyone have a comparison for how good/bad that is compared to other solutions, and what it means for practical usage, if that can be guessed at from a single number?

LibriSpeech test clean is without background noise, with a good microphone, and most likely biased to native speakers (it is 50/50 male/female at least). In summary, it's not what an ASR engine will encounter. However, the dataset is used as a common method to benchmark ASR engines and thus that number is valuable. The SpecAugment paper by Google for example claims a 2.5% word error rate [1] on that corpus (using only LibriSpeech for training data).

[1]: https://arxiv.org/pdf/1904.08779.pdf

Re: DeepSpeech 0.6

#9

Post by kbumsik » Thu, Dec 05, 2019, 10:21 AM UTC

Looks great. Is it related to any of Mozilla's product?

Re: DeepSpeech 0.6

#10

Post by bayesian_horse » Thu, Dec 05, 2019, 10:45 AM UTC

I just found https://voice.mozilla.org/

Besides being a great resource for speech analysis, this could be a real game changer for acquiring listening comprehension in a foreign language.

I feel that even after a few years of learning a new language I still have trouble with listening. Part of that is that it's often all or nothing, even one or two unknown words in a sentence means I can't understand the sentence. But worse is that most language teaching materials use a very small set of native speakers, which deprives the learner's brain of being able to generalize.