[ 
https://issues.apache.org/jira/browse/TIKA-94?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17286834#comment-17286834
 ] 

Lewis John McGibbney edited comment on TIKA-94 at 2/19/21, 3:49 AM:
--------------------------------------------------------------------

[~peterkronenberg] took a cursory look at vosk today. I am not clear on
# Whether a Java API actually exists? Whe directory seems to be empty but I 
will follows up with the project, and
# What the project licensing is... again the repository didn't appear to have 
an license so again I will follows up with the project

For the time being we are implementing a *tika-transcribe* module which will 
basically mimic the design pattern used for *tika-translate*. As Hackillinois 
is only a 3 week program, we will deliver one implementation for the time 
being... https://aws.amazon.com/transcribe/

The new API will be called *Tika.transcribe*


was (Author: lewismc):
[~peterkronenberg] took a cursory look at vosk today. I am not clear on
# Whether a Java API actually exists? Whe directory seems to be empty but I 
will follows up with the project, and
# What the project licensing is... again the repository didn't appear to have 
an license so again I will follows up with the project

For the time being we are implementing a *tika-speech* module which will 
basically mimic the design pattern used for *tika-translate*. As Hackillinois 
is only a 3 week program, we will deliver one implementation for the time 
being... https://aws.amazon.com/transcribe/

The new API will be called *Tika.transcribe*

> Speech recognition
> ------------------
>
>                 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)

Reply via email to