[TIKA-94] Speech-to-text transcription

• Type: New Feature
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Fix Version/s: 1.27
• Component/s: parser
• Labels: new-parser tika-transcription
• Assignee: Lewis John McGibbney
• Reporter: Jukka Zitting
• Created: 12/Nov/07 02:14
• Updated: 12/May/21 18:02
• Resolved: 03/May/21 23:31

Description

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.

Issue Links

• relates to: TIKA-3384 Convert new transcribe package to a Parser
• links to: GitHub Pull Request #406