Speech-to-text app for PyTorch?

For discussions about programming, programming questions/advice, and projects that don't really have anything to do with Puppy.
Post Reply
Message
Author
alvanorichie

Speech-to-text app for PyTorch?

#1 Post by alvanorichie »

Hello,

I don't know if its the right place to ask. What's the best API to look for speech to text integration in PyTorch?
Last edited by alvanorichie on Tue 18 Feb 2020, 10:51, edited 1 time in total.
Top
s243a
Posts: 2580
Joined: Tue 02 Sep 2014, 04:48
Contact:
Contact s243a

Re: Speech to text app?

#2 Post by s243a »

alvanorichie wrote:Hello,

I don't know if its the right place to ask. What's the best API to look for speech to text integration in PyTorch?
I use espeak (or espeak-ng) for text to speech. You can call it from python if you want. However, I'm sure you are probably looking for a python implementation.
Find me on [url=https://www.minds.com/ns_tidder]minds[/url] and on [url=https://www.pearltrees.com/s243a/puppy-linux/id12399810]pearltrees[/url].
Top
User avatar
technosaurus
Posts: 4853
Joined: Mon 19 May 2008, 01:24
Location: Blue Springs, MO
Contact:
Contact technosaurus

#3 Post by technosaurus »

Carnegie Mellon has/had great speech speech synthesis and recognizition tools. I am most familiar with their Flite ( text2speech ) and pocket-sphinx ( speech2text )utilities. They're pretty light and have permissive licenses and c bindings which makes them useable in nearly any programming language.
Check out my [url=https://github.com/technosaurus]github repositories[/url]. I may eventually get around to updating my [url=http://bashismal.blogspot.com]blogspot[/url].
Top
jamesbond
Posts: 3433
Joined: Mon 26 Feb 2007, 05:02
Location: The Blue Marble

#4 Post by jamesbond »

Python binding for espeak-ng:

Code: Select all

https://pypi.org/project/py-espeak-ng/
Fatdog64 forum links: [url=http://murga-linux.com/puppy/viewtopic.php?t=117546]Latest version[/url] | [url=https://cutt.ly/ke8sn5H]Contributed packages[/url] | [url=https://cutt.ly/se8scrb]ISO builder[/url]
Top
User avatar
technosaurus
Posts: 4853
Joined: Mon 19 May 2008, 01:24
Location: Blue Springs, MO
Contact:
Contact technosaurus

#5 Post by technosaurus »

Espeak is text to speech... thought the original question was speech to text.

There are plenty of python bindings for pocket sphinx but I can't recommend a specific project since I have only used it in C directly. Hopefully the python bindings have simplified it a bit because the C ABI is almost too extensive.
Check out my [url=https://github.com/technosaurus]github repositories[/url]. I may eventually get around to updating my [url=http://bashismal.blogspot.com]blogspot[/url].
Top
jamesbond
Posts: 3433
Joined: Mon 26 Feb 2007, 05:02
Location: The Blue Marble

#6 Post by jamesbond »

Of course. What was I thinking. sphinx it is.
Fatdog64 forum links: [url=http://murga-linux.com/puppy/viewtopic.php?t=117546]Latest version[/url] | [url=https://cutt.ly/ke8sn5H]Contributed packages[/url] | [url=https://cutt.ly/se8scrb]ISO builder[/url]
Top
lmemsm
Posts: 51
Joined: Wed 27 Jun 2012, 15:01

Re: Speech-to-text app for PyTorch?

#7 Post by lmemsm »

alvanorichie wrote:Hello,

I don't know if its the right place to ask. What's the best API to look for speech to text integration in PyTorch?
I've been looking for some decent FLOSS text to speech tools/libraries as well. The only ones I've been able to find that are not Internet based are sphinx and kaldi.

Sphinx was already mentioned and here's a link to Kaldi:
https://github.com/kaldi-asr/kaldi

Would love to find other options.
Top
Post Reply

Return to “Programming”