Models for automatic g2p for Icelandic (20.10)

Nikulásdóttir, Anna Björk

Models for automatic g2p for Icelandic (20.10)

Clarin IS Repository

Authors: Nikulásdóttir, Anna Björk

Item identifier: http://hdl.handle.net/20.500.12537/84

Project URL: https://github.com/grammatek/g2p-lstm

Date issued: 2020-10-01

Type: toolService

Language(s): Icelandic

Description: Grapheme-to-phoneme (g2p) models for Icelandic, trained on an encoder-decoder LSTM neural network. The models are delivered with scripts for automatic transcription of Icelandic in the standard pronunciation variation, in the northern variation, north-east variation, and the south variation. To run the scripts the user needs to install Fairseq (see Readme in the project repository). Hljóðritunarlíkön fyrir íslensku, þjálfuð á LSTM tauganeti. Líkönunum fylgja skriftur til þess að hljóðrita íslensku skv. hefðbundnum framburði, harðmæli, rödduðum framburði og hv-framburði. Til þess að keyra skrifturnar þarf notandi að setja upp Fairseq (sjá nánari skjölun með verkefninu).

Publisher: Grammatek ehf.

Subject(s): phonetics pronunciation grapheme-to-phoneme models phonetic transcription dialectal variation g2p

Collection(s): Clarin IS

Show full item record

Files in this item

This item is

Publicly Available

and licensed under:
Apache License 2.0

Name: g2p-lstm-master.zip
Size: 312.91 MB
Format: application/zip
Description: Unknown
MD5: a5973c78612352df215abd14c0c5a296

Download file Preview

File Preview

g2p-lstm-master
- transcribe_ice_south1 kB
- transcribe_ice_northeast1 kB
- data-bin
  - standard
    - valid.standard.graphemes-standard.phonemes.standard.graphemes.idx11 kB
    - dict.standard.graphemes.txt286 B
    - valid.standard.graphemes-standard.phonemes.standard.graphemes.bin20 kB
    - valid.standard.graphemes-standard.phonemes.standard.phonemes.idx11 kB
    - test.standard.graphemes-standard.phonemes.standard.graphemes.idx11 kB
    - valid.standard.graphemes-standard.phonemes.standard.phonemes.bin19 kB
    - train.standard.graphemes-standard.phonemes.standard.phonemes.idx67 kB
    - test.standard.graphemes-standard.phonemes.standard.graphemes.bin20 kB
    - dict.standard.phonemes.txt430 B
    - test.standard.graphemes-standard.phonemes.standard.phonemes.idx11 kB
    - train.standard.graphemes-standard.phonemes.standard.phonemes.bin115 kB
    - train.standard.graphemes-standard.phonemes.standard.graphemes.idx67 kB
    - test.standard.graphemes-standard.phonemes.standard.phonemes.bin19 kB
    - train.standard.graphemes-standard.phonemes.standard.graphemes.bin121 kB
  - north_east
    - test.north_east.graphemes-north_east.phonemes.north_east.graphemes.bin20 kB
    - valid.north_east.graphemes-north_east.phonemes.north_east.graphemes.idx11 kB
    - test.north_east.graphemes-north_east.phonemes.north_east.phonemes.idx11 kB
    - train.north_east.graphemes-north_east.phonemes.north_east.graphemes.idx67 kB
    - valid.north_east.graphemes-north_east.phonemes.north_east.graphemes.bin20 kB
    - train.north_east.graphemes-north_east.phonemes.north_east.graphemes.bin122 kB
    - test.north_east.graphemes-north_east.phonemes.north_east.phonemes.bin19 kB
    - dict.north_east.graphemes.txt286 B
    - valid.north_east.graphemes-north_east.phonemes.north_east.phonemes.idx11 kB
    - train.north_east.graphemes-north_east.phonemes.north_east.phonemes.idx67 kB
    - dict.north_east.phonemes.txt441 B
    - valid.north_east.graphemes-north_east.phonemes.north_east.phonemes.bin19 kB
    - train.north_east.graphemes-north_east.phonemes.north_east.phonemes.bin116 kB
    - test.north_east.graphemes-north_east.phonemes.north_east.graphemes.idx11 kB
  - south
    - test.south.graphemes-south.phonemes.south.graphemes.bin20 kB
    - train.south.graphemes-south.phonemes.south.phonemes.bin115 kB
    - dict.south.graphemes.txt286 B
    - test.south.graphemes-south.phonemes.south.phonemes.idx11 kB
    - train.south.graphemes-south.phonemes.south.graphemes.idx67 kB
    - valid.south.graphemes-south.phonemes.south.phonemes.idx11 kB
    - dict.south.phonemes.txt431 B
    - test.south.graphemes-south.phonemes.south.phonemes.bin19 kB
    - valid.south.graphemes-south.phonemes.south.graphemes.idx11 kB
    - train.south.graphemes-south.phonemes.south.graphemes.bin121 kB
    - valid.south.graphemes-south.phonemes.south.phonemes.bin19 kB
    - test.south.graphemes-south.phonemes.south.graphemes.idx11 kB
    - train.south.graphemes-south.phonemes.south.phonemes.idx67 kB
    - valid.south.graphemes-south.phonemes.south.graphemes.bin20 kB
  - north
    - train.north.graphemes-north.phonemes.north.graphemes.idx67 kB
    - test.north.graphemes-north.phonemes.north.graphemes.idx11 kB
    - test.north.graphemes-north.phonemes.north.phonemes.idx11 kB
    - valid.north.graphemes-north.phonemes.north.graphemes.idx11 kB
    - train.north.graphemes-north.phonemes.north.graphemes.bin122 kB
    - test.north.graphemes-north.phonemes.north.graphemes.bin20 kB
    - valid.north.graphemes-north.phonemes.north.phonemes.idx11 kB
    - train.north.graphemes-north.phonemes.north.phonemes.idx67 kB
    - dict.north.phonemes.txt431 B
    - test.north.graphemes-north.phonemes.north.phonemes.bin19 kB
    - valid.north.graphemes-north.phonemes.north.graphemes.bin20 kB
    - valid.north.graphemes-north.phonemes.north.phonemes.bin19 kB
    - train.north.graphemes-north.phonemes.north.phonemes.bin116 kB
    - dict.north.graphemes.txt286 B
- README.md1 kB
- transcribe_ice_north1 kB
- transcribe_ice_standard1 kB
- environment.yml142 B
- checkpoints
  - south-256-.3-s-s
    - checkpoint_last.pt85 MB
  - standard-256-.3-s-s
    - checkpoint_last.pt85 MB
  - north_east-256-.3-s-s
    - checkpoint_last.pt85 MB
  - north-256-.3-s-s
    - checkpoint_last.pt85 MB

Models for automatic g2p for Icelandic (20.10)

Files in this item

Partners, Coordination, Funding

Repository

More