[
https://issues.apache.org/jira/browse/TIKA-94?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17294795#comment-17294795
]
Lewis John McGibbney commented on TIKA-94:
------------------------------------------
This makes perfect sense to me. At the end of the day, we want to be processing
an InputStream (regardless of what data is contained inside) and returning
text. Ultimately, let's move this to a parser.
As phase 1 however, I propose that (once reviewed and approved) we merge
tika-transcribe module so that it can be further socialized. We can then do
some restructuring to make it align with the Tika 2.X architecture.
How does that grab you?
> 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)
