Joe Pfeiffer wrote: > I wasn't keeping track of statistics (I wasn't conducting an experiment, > I had a pamphlet that needed to be recreated and then edited), but the > results were very very close to 100% I certainly spent a lot more time > on reformatting and editing than I did proofreading.
ok but because you completed a simple task, you can not conclude it is working good. I mean good for you. I have tried many programs. Couple of OCR for example and I compared with commercial OCR. I tried festival, viavoice and many others TTS and STT - nothing useful - just a prove of concept or incomplete useless code. Yes it is useless compared to commercial tools, so again if you want good results in this area it should be commercial. It is interesting to know if something runs under linux.
