{"id":104737,"date":"2022-07-30T09:37:00","date_gmt":"2022-07-30T07:37:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0"},"modified":"2022-07-30T09:37:00","modified_gmt":"2022-07-30T07:37:00","slug":"vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/vypusk-sistemy-mashinnogo-perevoda-opennmt-2-28-0","title":{"rendered":"Release of the OpenNMT Machine Translation System 2.28.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
The release of the OpenNMT 0.28.0 machine translation system has been published. This system utilizes methods of machine learning. To build the neural network, the project leverages the capabilities of the TensorFlow deep learning library. The code for the modules developed by the OpenNMT project is written in Python and is distributed under the MIT license. Pre-trained models are available for English, German, and Catalan, while models for other languages can be created independently based on datasets from the OPUS project (two files are provided for training the system \u2014 one with sentences in the source language and another with high-quality translations of those sentences into the target language). <\/p>\n
The project is being developed with the participation of SYSTRAN, a company specializing in machine translation tools, and a group of researchers from Harvard, who are creating human language models for machine learning systems. The user interface is maximally simplified and only requires specifying the input file with text and the file for saving the translation result. The extension system allows for implementing additional functionality based on OpenNMT, such as self-referencing, text classification, and subtitle generation. <\/p>\n
Using TensorFlow allows the exploitation of GPU capabilities to accelerate the neural network training process. To facilitate the product's distribution, the project is also developing a self-sufficient version of the translator in C++ \u2014 CTranslate2, which utilizes pre-trained models without relying on additional dependencies. <\/p>\n