As part of my general A.I. strategy, I am evaluating Sphinx4. For fun, I am trying it on machine voices [from cereproc.com].
The results are promising. Some stuff comes out wrong, but then again it is safe to say the "William" voice swallows syllables from time to time. Both products could be optimized, naturally... :-)
The program actually runs all by itself. It will download all libraries & data automatically. Just get tinybrain.de/x30.jar, run it and enter "1004801", the rest should be self-explanatory. Right-click in programs list to add parameters (text to say+recognize). Mind you there's a bug in the MP3 to WAV converter that stops the whole thing sometimes.
I'm really happy to have found a way to distribute software installation- and hassle-free like this. I'd love to know if it works for you?
Hi there.
As part of my general A.I. strategy, I am evaluating Sphinx4. For fun, I am trying it on machine voices [from cereproc.com].
The results are promising. Some stuff comes out wrong, but then again it is safe to say the "William" voice swallows syllables from time to time. Both products could be optimized, naturally... :-)
Code: http://tinybrain.de/1004801
The program actually runs all by itself. It will download all libraries & data automatically. Just get tinybrain.de/x30.jar, run it and enter "1004801", the rest should be self-explanatory. Right-click in programs list to add parameters (text to say+recognize). Mind you there's a bug in the MP3 to WAV converter that stops the whole thing sometimes.
I'm really happy to have found a way to distribute software installation- and hassle-free like this. I'd love to know if it works for you?
Anyone in the mood for making more AI? :-)
Cheers,
Stefan
ai1.lol
Last edit: Stefan Reich 2016-08-31