You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@tika.apache.org by "Tim Allison (Jira)" <ji...@apache.org> on 2021/03/03 20:03:00 UTC

[jira] [Commented] (TIKA-94) Speech-to-text transcription

    [ https://issues.apache.org/jira/browse/TIKA-94?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17294786#comment-17294786 ] 

Tim Allison commented on TIKA-94:
---------------------------------

[~lewismc] please forgive my delay.

I finally had a chance to look at this today a bit. I'm really excited to add this to Tika and to add an offline STT system as well (sphinx/Kaldi?). My personal preference would be to turn this into a parser like the TesseractOCRParser and not create a new interface. So, y, I mean literally _extends AbstractParser implements Initializable_.

I'm happy to chip in and do the conversion either on the source branch or on a TIKA-94 branch in our repo.

> Speech-to-text transcription
> ----------------------------
>
>                 Key: TIKA-94
>                 URL: https://issues.apache.org/jira/browse/TIKA-94
>             Project: Tika
>          Issue Type: New Feature
>          Components: parser
>            Reporter: Jukka Zitting
>            Assignee: Lewis John McGibbney
>            Priority: Minor
>              Labels: new-parser
>
> Like OCR for image files (TIKA-93), we could try using speech recognition to extract text content (where available) from audio (and video!) files.
> The CMU Sphinx engine (http://cmusphinx.sourceforge.net/) looks promising and comes with a friendly license.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)