{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pymarian-fast-neural-machine-translation-and","title":"PyMarian: Fast Neural Machine Translation and Evaluation in Python","arxiv_id":"2408.11853","date":"2024-08-15","proceeding":null,"authors":["Thamme Gowda","Roman Grundkiewicz","Elijah Rippeth","Matt Post","Marcin Junczys-Dowmunt"],"abstract":"The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software written in lower-level programming languages like C++ retain advantages in speed. We describe a Python interface to Marian NMT, a C++-based training and inference toolkit for sequence-to-sequence models, focusing on machine translation. This interface enables models trained with Marian to be connected to the rich, wide range of tools available in Python. A highlight of the interface is the ability to compute state-of-the-art COMET metrics from Python but using Marian's inference engine, with a speedup factor of up to 7.8$\\times$ the existing implementations. We also briefly spotlight a number of other integrations, including Jupyter notebooks, connection with prebuilt models, and a web app interface provided with the package. PyMarian is available in PyPI via $\\texttt{pip install pymarian}$.","url_abs":"https://arxiv.org/abs/2408.11853v1","url_pdf":"https://arxiv.org/pdf/2408.11853v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.11853","atlas_url":"https://app.syntology.ai/?focus=2408.11853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11853"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/pascanur/GroundHog","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/OpenNMT/CTranslate2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"found_in_text":{"samples":6,"ran":6,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"57d2b237f2f6c212","entry":"get_vocabs","repo":"OpenNMT/CTranslate2","repo_kind":"found_in_text","path":"python/ctranslate2/converters/eole_ct2.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/converters/eole_ct2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57d2b237f2f6c212"}},{"code_sha256_prefix":"794ef6f28819556a","entry":"get_vocabs","repo":"OpenNMT/CTranslate2","repo_kind":"found_in_text","path":"python/ctranslate2/converters/opennmt_py.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/converters/opennmt_py.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"794ef6f28819556a"}},{"code_sha256_prefix":"de4708f955404e2c","entry":"index_spec","repo":"OpenNMT/CTranslate2","repo_kind":"found_in_text","path":"python/ctranslate2/specs/model_spec.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/specs/model_spec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de4708f955404e2c"}},{"code_sha256_prefix":"241f78b9e78ef2ea","entry":"load_vocab","repo":"OpenNMT/CTranslate2","repo_kind":"found_in_text","path":"python/ctranslate2/converters/marian.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/converters/marian.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"241f78b9e78ef2ea"}},{"code_sha256_prefix":"11b161ee05f4007c","entry":"print_time","repo":"pascanur/GroundHog","repo_kind":"found_in_text","path":"groundhog/utils/utils.py","file_url":"https://github.com/pascanur/GroundHog/blob/HEAD/groundhog/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"11b161ee05f4007c"}},{"code_sha256_prefix":"dbf102ede3867ea9","entry":"register_loader","repo":"OpenNMT/CTranslate2","repo_kind":"found_in_text","path":"python/ctranslate2/converters/transformers.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/converters/transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbf102ede3867ea9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}