Icon

CRAFTED_​speech2text_​public

This Knime workflow is part of a suite of tools developed for the CRAFTED project (https://pro.europeana.eu/project/crafted).

This workflow will extract text from a sound file, using the Google vision API. The workflow builds upon the results from the workflow 'CRAFTED_get-data-MINT_public'.

Workflow components:

1. read data about the sound file from a MongoDB and loads the image
3. execute a request to Google Vision speech to text engine
5. write the result in W3C annotation format to a file
6. write the result in W3C annotation format to the MongoDB

Configuration:
- set mongoDB connection to read image metadata [see workflow 'CRAFTED_get-data-MINT_public]
- set CP name and dataset ID
- set API key in Post Request node
- set mongoDB connection to write results
- set path to annotations folder

Requirements:
- Knime (https://www.knime.com/)
- MongoDB Compass (see https://www.mongodb.com/products/compass)
- a Google Vision account and API_KEY (see https://cloud.google.com/speech-to-text)

get dataSET CP NAMESET LANGUAGE CODETESTERNode 21Node 375output pathNode 383Node 424Node 425Node 426Node 428MongoDB Connector MongoDB Reader Variable Creator JSON Path Row Filter MongoDB Connector JSON Writer String Manipulation(Variable) String to Path(Variable) MongoDB Writer processstandard model create annotation post S2T request- standard model GET resultsstandard model get dataSET CP NAMESET LANGUAGE CODETESTERNode 21Node 375output pathNode 383Node 424Node 425Node 426Node 428MongoDB Connector MongoDB Reader Variable Creator JSON Path Row Filter MongoDB Connector JSON Writer String Manipulation(Variable) String to Path(Variable) MongoDB Writer processstandard model create annotation post S2T request- standard model GET resultsstandard model

Nodes

Extensions

Links