| dc.contributor.author | Snæbjarnarson, Vésteinn |
| dc.contributor.author | Símonarson, Haukur Barri |
| dc.contributor.author | Þorsteinsson, Vilhjálmur |
| dc.date.accessioned | 2020-09-29T15:57:06Z |
| dc.date.available | 2020-09-29T15:57:06Z |
| dc.date.issued | 2020-09-28 |
| dc.identifier.uri | http://hdl.handle.net/20.500.12537/72 |
| dc.description | Code and models required to run the GreynirT2T Transformer NMT system for translation between English and Icelandic. Includes a Docker-Compose file that starts a REST web server making the translation models available to clients. Forrit og líkön til að keyra GreynirT2T Transformer vélþýðingarlíkön fyrir þýðingar á milli íslensku og ensku. Docker-Compose uppskrift keyrir upp REST vefþjón sem gerir líkönin aðgengileg netbiðlurum. |
| dc.language.iso | isl |
| dc.language.iso | eng |
| dc.publisher | Miðeind ehf. |
| dc.rights | The MIT License (MIT) |
| dc.rights.uri | https://opensource.org/licenses/mit-license.php |
| dc.rights.label | PUB |
| dc.source.uri | https://github.com/mideind/nnserver |
| dc.subject | machine translation |
| dc.subject | transformer |
| dc.subject | neural machine translation |
| dc.title | GreynirT2T Serving - En--Is NMT Inference and Pre-trained Models (1.0) |
| dc.type | toolService |
| metashare.ResourceInfo#ContentInfo.detailedType | service |
| metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
| has.files | yes |
| branding | Clarin IS Repository |
| demo.uri | https://velthyding.is/ |
| contact.person | Vilhjálmur Þorsteinsson clarin@mideind.is Miðeind ehf. |
| sponsor | Ministry of Education, Science and Culture Baseline in machine translation (V3) Language Technology for Icelandic 2019-2023 nationalFunds |
| files.size | 390666700 |
| files.count | 2 |
Files in this item
Download all files in item (372.57 MB)
- Name
- greynirt2t-inference.models.EN-IS.tar.gz
- Size
- 372.29 MB
- Format
- application/gzip
- Description
- Translations models and start script (enough for inerence)
- MD5
- b322d674ab600e6e8a5bbb0803e0b7d0
- greynirt2t-inference
- README.md1 kB
- conf
- models
- models.conf633 B
- translate_isen16k_v4_tagged_bt_noised_mix3-avg-6-ckpt-1_125m-partial
- 1589804160
- saved_model.pbtxt7 MB
- variables
- variables.index9 kB
- variables.data-00000-of-00001200 MB
- 1589804160
- translate_enis16k_v4_untagged_bt.bt.untagged-avg-ckpt-2_8m-partial
- 1586015138
- saved_model.pbtxt7 MB
- variables
- variables.index9 kB
- variables.data-00000-of-00001200 MB
- 1586015138
- models
- docker-compose.yml529 B
- Name
- nnserverv0.1.tar.gz
- Size
- 284.01 KB
- Format
- application/gzip
- Description
- Code for inference server
- MD5
- bbde45f808e7f60665081ddacf5bb499
- nnserver-0.1
- setup.py1 kB
- README.md1 kB
- .gitignore1 kB
- nnserver
- systemd
- nnserver.env95 B
- model_server.service1 kB
- nnserver.service617 B
- __init__.py1 kB
- resources
- vocab.translate_enis16k_v4.en.nmt-bpe152 kB
- vocab.translate_enis16k_v4.is.nmt-bpe155 kB
- parsing_tokens_191202.txt32 kB
- parsing_tokens_180729.txt38 kB
- vocab.translate_enis16k.16384.subwords141 kB
- vocab.enis.16384.subwords133 kB
- greynir_parsing.py2 kB
- scripts
- validate.sh1 kB
- run_training.sh680 B
- env.sh743 B
- train.sh433 B
- decode.sh387 B
- export.sh419 B
- do_generate_train_validate.sh190 B
- generate_data.sh376 B
- composite_encoder.py10 kB
- utils.py185 B
- requirements.txt54 B
- main.py15 kB
- tests.py564 B
- bin
- model_server.sh652 B
- nnserver55 B
- __init__.py702 B
- systemd
- docker
- Dockerfile327 B
- docker-compose.yml529 B
- LICENSE34 kB
- SYSTEMD_README.org5 kB
- pax_global_header52 B