Tensor2tensor Translation for Docker

Tensor2tensor Translation for Docker

LINDAT / CLARIAH-CZ

Autoři: Variš, Dušan

Identifikátor: http://hdl.handle.net/11234/1-3734

URL dema: https://lindat.mff.cuni.cz/services/translation/

Datum vydání: 2021-08-23

Typ: toolService

Popis: This submission contains Dockerfile for creating a Docker image with compiled Tensor2tensor backend with compatible (TensorFlow Serving) models available in the Lindat Translation service (https://lindat.mff.cuni.cz/services/transformer/). Additionally, the submission contains a web frontend for simple in-browser access to the dockerized backend service. Tensor2Tensor (https://github.com/tensorflow/tensor2tensor) is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Nakladatel: Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)

Klíčová slova: machine translation neural machine translation tensor2tensor docker

Kolekce: LINDAT / CLARIAH-CZ Data & Tools

Zobrazit celý záznam

Soubory tohoto záznamu

Licenční kategorie:

Publicly Available

Licence: Apache License 2.0

Název: lindat-transformer-docker.zip
Velikost: 13.76 KB
Formát: application/zip
Popis: Installation Archive
MD5: 81c504b737f92af54959cabe0a5e76e8

Stáhnout soubor Náhled

Náhled souboru

lindat-transformer-docker
- translate.sh1 kB
- t2t-serving-adapter.py8 kB
- models
  - available_models.txt334 B
  - model.config.template166 B
  - model.config.gen121 B
  - get_models.sh338 B
  - batching.config60 B
- README.md909 B
- Dockerfile.base1 kB
- usr_dir
  - my_registrations.py3 kB
  - __init__.py61 B
- start.sh632 B
- Dockerfile.template197 B
- Dockerfile.build.sh294 B
- LICENSE11 kB