botium-speech-processing
AI
speech recognition and synthesis
SHOW HN2020
Legend
botium-speech-processing
Text-to-speech and speech-to-text open-source software stack
github.com#speech-to-text#text-to-speech#kaldi#marytts#open source speech
How HN took it
6 positive, 13 neutral or asking, 2 mixed, 4 critical, out of 25 comments about the project. Thread score +0.09.
Performance: 1 for, 2 againstExecution: 2 for, 1 againstIdea: 1 for, 0 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Polished demo and well-built work
From 1 comment
That's fantastic work and the demo is very well done. Thanks for sharing it. You obviously put a lot of hard work into it. Feels super polished.
tomcam on HN
Easy-to-use API that provides a quick voice boilerplate
From 2 comments
it means: easy to install, easy to use, medium performance. no further know-how needed. compared to the total effort for selecting, training, deploying speech recogniction and…
ftreml on HN> just a small server, hope that it wont crash when posting > the link here In all honesty I was just looking for some pre-processed examples. The API itself seems intuitive…
bArray on HN
Objections
Text-to-speech quality is robotic and weaker than commercial engines
From 2 comments
I've built a speech synthesis system with Marytts before, it works, but unfortunately, the quality is not very good, HMM and unit selection speech synthesis are now very old…
ayumu722 on HN> just a small server, hope that it wont crash when posting > the link here In all honesty I was just looking for some pre-processed examples. The API itself seems intuitive…
bArray on HN
Recognition is less accurate than cloud services and Kaldi is outdated compared to newer models
From 2 comments
It is very unlikely a E2E toolkit can outperform kaldi if they're trained on the same data. Also I suspect these guys aren't using the latest kaldi architectures.
Nimitz14 on HNCool! Thanks! I've tried both wav2letter and DeepSpeech, and now this, but I get very poor results even with short sentences (compared to Google's proprietary services). Would it…
z3t4 on HN
Large disk requirement of about 40GB
From 1 comment
So why is 40gigs of free space needed?
polishdude20 on HN
Requests
Support for more languages
From 2 comments
You should indicate somewhere which languages are supported. You mention Deepspeech German in the credits, but did you use it to implement support for German or just to inform…
yorwba on HNWhich languages are supported?
ajaviaad on HN
Additional STT/TTS backends such as Tacotron2 or wav2letter
From 3 comments
I built something quite similar on my own product. Is there any interest on adding more STT/TTS backends to the software? Think services like Lyrebird or Trint. I could…
pouta on HNI've built a speech synthesis system with Marytts before, it works, but unfortunately, the quality is not very good, HMM and unit selection speech synthesis are now very old…
ayumu722 on HNso this is a real cool project. as soon as you finished your training I will be happy to add it as option (or maybe default setup) in the botium speech processing setup (if you…
ftreml on HN
Live demo
From 2 comments
Would love to see a live demo. MaryTTS demo link is broken.
mariushn on HNWould be cool with a web demo.
z3t4 on HN
Questions
Which languages are supported
From 1 comment
Which languages are supported?
ajaviaad on HN
Performance compared to DeepSpeech, wav2letter and cloud services
From 2 comments
Any idea how it compares to Mozilla's DeepSpeech?
dsteinman on HNAre there any performance metrics of this versus other offline and cloud based services?
monkeydust on HN
Real-time streaming support
From 1 comment
Any recommendations for a real time solution? I maintain a platform which features live video events we'd like to add captioning and so far can only see IBM Watson providing a…
CommanderData on HN
Alternatives named
Mozilla DeepSpeech
From 2 comments
> deepspeech was evaluated, but right now kaldi provides better performance Was this before the streaming API was added to DeepSpeech? I recently did some testing with it, and it…
magicalhippo on HNMozilla DeepSpeech has seen significant improvements in the quality of results it provides (and RAM/CPU usage) since early December, the accuracy of transcriptions has…
StudentStuff on HN
wav2letter++
From 1 comment
Facebook has released wav2letter++. I'd wager that will outperform kaldi by a wide margin.
grizzles on HN
Google and Amazon cloud speech services
From 1 comment
picotts is a command line tool. marytts is a client/server tool. (both included in botium speech processing and callable with curl). high quality with google cloud speech and…
ftreml on HN
Festival speech synthesis
From 1 comment
If marytts is so good, why are we in many linux distros still using https://en.wikipedia.org/wiki/Festival_Speech_Synthesis_System as our default tts system?
bobmaxup on HN
CMU Sphinx
From 1 comment
Can anyone in the space expand on why it's increasingly rare to see people using/building on Sphinx[0]? Do people avoid it simply because of an impression that it won't be good…
hardwaresofton on HN