Automatic Speech Recognition for Dutch

This is a web-based automatic speech recogniser for Dutch, capable of transcribing dutch speech recordings using multiple models.

Provided tools & services

Automatic Speech Recognition for Dutch

Type
  • Unknown

Automatic Transcription of Dutch Speech Recordings

This webservice uses automatic speech recognition to provide the transcriptions of recordings spoken in Dutch. You can upload and process only one file per project. For bulk processing and other questions, please contact Henk van den Heuvel at h.vandenheuvel@let.ru.nl.
Go to the WebApplication https://webservices.cls.ru.nl/asr_nl
Type
  • Web Application
Version
0.6.0
Service Provider
      Centre for Language and Speech Technology, Radboud University
Input data
Name
*.flac
Description
Flac file
Type
AudioObject
Encoding Format
audio/flac
Name
*.mp3
Description
MP3 file
Type
AudioObject
Encoding Format
audio/mpeg
Name
*.wav
Description
Wav file
Type
AudioObject
Encoding Format
audio/vnd.wave
Name
*.m4a
Description
M4A file
Type
AudioObject
Encoding Format
audio/mpeg
Name
*.mp4
Description
MP4 file
Type
AudioObject
Encoding Format
audio/mpeg
Name
*.ogg
Description
Ogg file
Type
AudioObject
Encoding Format
audio/vorbis
Output data
Name
*.txt
Description
Automatic transcription of the input recording
Type
DigitalDocument
Encoding Format
text/plain
Name
*.xml
Description
Automatic transcription of the input recording (full data) (AudioDoc XML)
Type
DigitalDocument
Encoding Format
text/xml
Name
*.ctm
Description
Automatic transcription of the input recording with timestamps (CTM)
Type
DigitalDocument
Encoding Format
text/plain
Name
*.ctm.spk
Description
Automatic transcription of the input recording with timestamps (CTM) and speaker diarisation
Type
DigitalDocument
Encoding Format
text/plain
Name
error.log
Description
Log file with (standard) error output
Type
DigitalDocument
Encoding Format
text/plain

Citation

You can cite this software using the following citation generated from its metadata:

Automatic Speech Recognition for Dutch 0.6.0 .
  • Centre for Language and Speech Technology
.

Logs & Reviews

Name
Automatic software metadata validation report for Automatic Speech Recognition for Dutch 0.6.0
Author
  • codemetapy validator using software.ttl
Date
2023-05-30 04:00:24
Review
Please consult the CLARIAH Software Metadata Requirements at https://github.com/CLARIAH/clariah-plus/blob/main/requirements/software-metadata-requirements.md for an in-depth explanation of any found problems

Validation of Automatic Speech Recognition for Dutch 0.6.0 was successful (score=3/5), but there are some warnings which should be addressed:

1. Warning: Software source code *SHOULD* link to a continuous integration service that builds the software and runs the software's tests (This is missing in the metadata)
2. Info: Software source code *MAY* express the programming language(s) used (This is missing in the metadata)
3. Info: An interface type *SHOULD* be expressed: Software source code should define one or more target products that are the resulting software applications offering specific interfaces (The metadata does express this currently, but something is wrong in the way it is expressed. Is the type/class valid?)
4. Warning: Documentation *SHOULD* be expressed (This is missing in the metadata)
5. Info: Reference publications *SHOULD* be expressed, if any (This is missing in the metadata)
6. Info: The funder *SHOULD* be acknowledged (This is missing in the metadata)
7. Info: The technology readiness level *SHOULD* be expressed (This is missing in the metadata)
Rating
★ ★ ★ ☆ ☆ 
(log file starts at Tue May 30 04:00:22 UTC 2023)

[harvester info] --> Processing asr_nl (https://github.com/opensource-spraakherkenning-nl/asr_nl) [Tue May 30 04:00:22 UTC 2023]

[harvester info] Git updating cached clone of https://github.com/opensource-spraakherkenning-nl/asr_nl...

[harvester info] Found release v0.6.0

[harvester info] Using 'v0.6.0'

[harvester info] Git reference: v0.6.0

[harvester info] Scanning directory /tmp/codemeta-harvester.cache/asr_nl for harvestable resources...

[harvester info] found codemeta.json for asr_nl (md5sum 34c06eec80adf5509cbcd79039f6fd35); **NOTE: this is considered authoritative and most other detection methods will be skipped now!**

[harvester info] Inferring repostatus information from git activity (used only as a fallback if not explicitly provided)...

[harvester info] Inferred repostatus https://www.repostatus.org/#active

[harvester info] Looking for repostatus information in README.md in master branch...

-- begin log --

-- end log --

[harvester info] Found README.md

[harvester info] Reconciliating: codemetapy  --baseuri https://webservices.cls.ru.nl/portal --baseuri https://webservices.cls.ru.nl/portal --includecontext --addcontext https://w3id.org/nwo-research-fields --addcontext https://w3id.org/research-technology-readiness-levels --addcontextgraph https://vocabs.dariah.eu/rest/v1/tadirah/data?format=text/turtle --trl --identifier "asr_nl" --codeRepository "https://github.com/opensource-spraakherkenning-nl/asr_nl" --validate /etc/software.ttl --released --enrich --textv "Please consult the CLARIAH Software Metadata Requirements at https://github.com/CLARIAH/clariah-plus/blob/main/requirements/software-metadata-requirements.md for an in-depth explanation of any found problems" -O /tmp/out/asr_nl.codemeta.json /tmp/codemeta-harvester.cache//tmp/99-repostatus.asr_nl.codemeta.json /tmp/codemeta-harvester.cache//tmp/41-readme.asr_nl.codemeta.json /tmp/codemeta-harvester.cache//tmp/10-jsonld.asr_nl.codemeta.json 

-- begin log --

Passed 3 files/sources but specified 0 input types! Automatically guessing types...

Detected input types: [('/tmp/codemeta-harvester.cache//tmp/99-repostatus.asr_nl.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/41-readme.asr_nl.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/10-jsonld.asr_nl.codemeta.json', 'json')]

Adding to contextgraph: /tmp/turtle

Initial URI automatically generated, may be overriden later: https://webservices.cls.ru.nl/portal/asr-nl

Processing source #1 of 3

Parsing json-ld file from /tmp/codemeta-harvester.cache//tmp/99-repostatus.asr_nl.codemeta.json

    NOTE: Not a valid JSON-LD document, @context missing! Attempting to inject automatically...

    Injected (possibly temporary) URI https://webservices.cls.ru.nl/portal/asr-nl

[CODEMETA COMPOSITION (https://webservices.cls.ru.nl/portal/asr-nl)] processed 1 new triples, total is now 2

Processing source #2 of 3

Parsing json-ld file from /tmp/codemeta-harvester.cache//tmp/41-readme.asr_nl.codemeta.json

    NOTE: Not a valid JSON-LD document, @context missing! Attempting to inject automatically...

    Injected (possibly temporary) URI https://webservices.cls.ru.nl/portal/asr-nl

[CODEMETA COMPOSITION (https://webservices.cls.ru.nl/portal/asr-nl)] processed 1 new triples, total is now 3

Processing source #3 of 3

Parsing json-ld file from /tmp/codemeta-harvester.cache//tmp/10-jsonld.asr_nl.codemeta.json

    Injected (possibly temporary) URI https://webservices.cls.ru.nl/portal/asr-nl

[CODEMETA COMPOSITION (asr_nl)] overriding old https://codemeta.github.io/terms/readme (https://github.com/proycon/alpino_clam_webservice/blob/v0.6.0/README.md -> https://github.com/opensource-spraakherkenning-nl/asr_nl/blob/master/README.md)

[CODEMETA CORRECTION (asr_nl)] automatically converting spdx license URI from https:// to http:///

[CODEMETA COMPOSITION (asr_nl)] processed 67 new triples, total is now 67

Remapping URI to (possibly) new identifier and version component: https://webservices.cls.ru.nl/portal/asr-nl -> https://webservices.cls.ru.nl/portal/asr_nl/0.6.0

[CODEMETA VALIDATION (asr_nl)] done

[CODEMETA ENRICHMENT (asr_nl)] Guessing interface type https://w3id.org/software-types#WebApplication based on clues

[CODEMETA ENRICHMENT (asr_nl)] adding author https://webservices.cls.ru.nl/portal/stub/H-1e8e9a558bc27f1c as contributor

[CODEMETA ENRICHMENT (asr_nl)] adding author https://webservices.cls.ru.nl/portal/stub/H7e09eead053dd576 as contributor

[CODEMETA ENRICHMENT (asr_nl)] adding author https://webservices.cls.ru.nl/portal/stub/H6ac3ee15ccd544d9 as contributor

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #1: Warning: Software source code *SHOULD* link to a continuous integration service that builds the software and runs the software's tests (This is missing in the metadata)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #2: Info: Software source code *MAY* express the programming language(s) used (This is missing in the metadata)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #3: Info: An interface type *SHOULD* be expressed: Software source code should define one or more target products that are the resulting software applications offering specific interfaces (The metadata does express this currently, but something is wrong in the way it is expressed. Is the type/class valid?)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #4: Warning: Documentation *SHOULD* be expressed (This is missing in the metadata)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #5: Info: Reference publications *SHOULD* be expressed, if any (This is missing in the metadata)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #6: Info: The funder *SHOULD* be acknowledged (This is missing in the metadata)

VALIDATION https://webservices.cls.ru.nl/portal/asr_nl/0.6.0 #7: Info: The technology readiness level *SHOULD* be expressed (This is missing in the metadata)

-- end log --

[harvester info] Output written to /tmp/out/asr_nl.codemeta.json

[harvester info] Harvesting remote service URL https://webservices.cls.ru.nl/asr_nl/ for asr_nl: codemetapy  --baseuri https://webservices.cls.ru.nl/portal --baseuri https://webservices.cls.ru.nl/portal --includecontext --addcontext https://w3id.org/nwo-research-fields --addcontext https://w3id.org/research-technology-readiness-levels --addcontextgraph https://vocabs.dariah.eu/rest/v1/tadirah/data?format=text/turtle --trl -O "/tmp/codemeta-harvester.cache//tmp/asr_nl.codemeta.json" "/tmp/out/asr_nl.codemeta.json" "https://webservices.cls.ru.nl/asr_nl/"

-- begin log --

Passed 2 files/sources but specified 0 input types! Automatically guessing types...

Detected input types: [('/tmp/out/asr_nl.codemeta.json', 'json'), ('https://webservices.cls.ru.nl/asr_nl/', 'web')]

Adding to contextgraph: /tmp/turtle

Initial URI automatically generated, may be overriden later: https://webservices.cls.ru.nl/portal/asr-nl

Processing source #1 of 2

Parsing json-ld file from /tmp/out/asr_nl.codemeta.json

    Found main resource with URI https://webservices.cls.ru.nl/portal/asr_nl/0.6.0

    Injected (possibly temporary) URI https://webservices.cls.ru.nl/portal/asr-nl

[CODEMETA COMPOSITION (asr_nl)] processed 93 new triples, total is now 93

Processing source #2 of 2

Fallback: Obtaining metadata from remote URL https://webservices.cls.ru.nl/asr_nl/

    Service replied with content-type application/ld+json

    Parsing json...

    Found main resource with URI https://webservices.cls.ru.nl/asr_nl

    Injected (possibly temporary) URI https://webservices.cls.ru.nl/portal/webapplication/N62365a01686d5cbf3db611b583c689ed

Adding service (targetProduct) https://webservices.cls.ru.nl/asr_nl/

[CODEMETA COMPOSITION (asr_nl)] processed 80 new triples, total is now 174

Remapping URI to (possibly) new identifier and version component: https://webservices.cls.ru.nl/portal/asr-nl -> https://webservices.cls.ru.nl/portal/asr_nl/0.6.0

[CODEMETA VALIDATION (asr_nl)] done

-- end log --

[harvester info] <-- Finished processing asr_nl (https://github.com/opensource-spraakherkenning-nl/asr_nl) [Tue May 30 04:00:28 UTC 2023]

Metadata Properties

Version
0.6.0
Interface types
  • Web Application
Software website
Source code repository
 https://github.com/opensource-spraakherkenning-nl/asr_nl Stars are an indicator of the popularity of this project on GitHub
Keywords
  • dutch
  • nlp
  • speech recognition
Development Status
  • Active: The project has reached a stable, usable state and is being actively developed.
Issue Tracker (Support)
https://github.com/opensource-spraakherkenning-nl/asr_nl/issues The number of open issues on the issue tracker The number of closes issues on the issue tracker
Documentation
License
Author(s)
Maintainer(s)
Contributor(s)
Producer
Operating System
  • Linux
Software dependencies
  • Kaldi_NL
  • CLAM
  • kaldi
Metadata validation
★ ★ ★ ☆ ☆
Created
2017-04-02