{"id":948,"date":"2020-03-31T22:44:07","date_gmt":"2020-03-31T20:44:07","guid":{"rendered":"https:\/\/www.cjvt.starkmat.si\/template-projekt\/references\/"},"modified":"2025-09-29T08:46:56","modified_gmt":"2025-09-29T06:46:56","slug":"references","status":"publish","type":"page","link":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/","title":{"rendered":"Results"},"content":{"rendered":"

Results<\/h1>\n<\/div><\/section><\/div><\/div>\n

List of Results by Projects and Months<\/strong><\/h2>\n<\/div><\/section><\/div><\/div>\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
*No.<\/td>\nName<\/td>\nOrganization<\/td>\nType<\/td>\nTRL<\/td>\nLinks<\/td>\n<\/tr>\n
August 2024<\/strong><\/td>\n\u00a0<\/strong><\/td>\n<\/tr>\n
\u2002\u2002\u2002\u2002\u2002D1.1<\/td>\nAccessible Slovenian training dataset for dialogues and command requests.<\/strong><\/td>\nFRI<\/td>\ndata<\/td>\n3<\/td>\nAccess: GaMS-Instruct-GEN 1.0 | CLARIN.SI<\/a><\/td>\n<\/tr>\n
D1.2<\/td>\nLarge language corpus for conversational language and addressed terminological areas \u2013 first version.<\/td>\nFRI<\/td>\ndata<\/td>\n3<\/td>\nAccess: PoVeJMo-VeMo-Med 1.0 | CLARIN.SI<\/a><\/td>\n<\/tr>\n
D1.3<\/td>\nValidation corpus for large language models.<\/td>\nFRI<\/td>\ndata<\/td>\n3<\/td>\nAccess: slovenian-llm-eval | HuggingFace<\/a><\/td>\n<\/tr>\n
D2.1<\/td>\nOpen-access large generative language model tailored for dialogues and commands with a size of one billion parameters.<\/td>\nFRI<\/td>\nsoftware<\/td>\n3<\/td>\nAccess: GaMS-2B-Instruct | HuggingFace<\/a><\/td>\n<\/tr>\n
D3.1<\/td>\nTraining set with at least 10,000 examples.<\/td>\nSemantika<\/td>\ndata<\/td>\n5<\/td>\nAccess: GaMS-Instruct-DH 1.0 | CLARIN.SI<\/a><\/td>\n<\/tr>\n
D4.1<\/td>\nTraining set with specific dialogues and commands from the field of medical applications, consisting of at least 10,000 examples.<\/td>\nBetter<\/td>\ndata<\/td>\n5<\/td>\nAccess: GaMS-Instruct-MED 1.0 | CLARIN.SI<\/a><\/td>\n<\/tr>\n
D5.1<\/td>\nAnalysis of the possibilities of using speech and language technologies to improve the efficiency of human-machine communication in industrial environments.<\/td>\n\u0160pica<\/td>\ndocumentation<\/td>\n5<\/td>\nAccess: Analiza mo\u017enosti uporabe govornih in jezikovnih tehnologij | PDF<\/a> (in Slovene)<\/td>\n<\/tr>\n
D5.2<\/td>\nReport on the suitability of technical equipment and possible methods of integrating language and speech technologies in manufacturing environments.<\/td>\n\u0160pica<\/td>\ndocumentation<\/td>\n5<\/td>\nAccess: Poro\u010dilo o primernosti tehni\u010dne opreme in mo\u017enih na\u010dinih integracije jezikovnih in govornih tehnologij v proizvodnih okoljih | PDF<\/a> (in Slovene)<\/td>\n<\/tr>\n
D6.1<\/td>\nDevelopment of the initial plan and approaches for the effective use of large language models in IaC (Infrastructure as Code): Use and selection of training data, description of possible approaches.<\/td>\nXLAB<\/td>\ndocumentation<\/td>\n5<\/td>\nAccess: Dokumentacija in na\u010drt rabe podatkov in pristopov | PDF<\/a> (in Slovene)<\/td>\n<\/tr>\n
D6.2<\/td>\nFirst version of software enabling the use of language technologies in IaC, taking into account performance, robustness, and security limitations.<\/td>\nXLAB<\/td>\nsoftware<\/td>\n5<\/td>\nAccess: VeMo-IaC – v1 (opis) | PDF<\/a><\/td>\n<\/tr>\n
February 2025<\/strong><\/td>\n\u00a0<\/strong><\/td>\n<\/tr>\n
D1.4<\/td>\nTools for preparing lexical databases for model training and components for the HuggingFace pipeline for integrating open lexical forms.<\/td>\nFRI<\/td>\nsoftware<\/td>\n3<\/td>\nDescription of API routes for Digital dictionary database of Slovene:<\/p>\n

Digital Dictionary Database of Slovene – API Routes | CJVT Wiki<\/a><\/p>\n

API-routes test: \u00a0Redoc<\/a><\/p>\n

Swagger<\/a><\/p>\n

 <\/td>\n<\/tr>\n

D1.5<\/td>\nDedicated tokenizers for the Slovenian language \u2013 first version.<\/td>\nFRI<\/td>\nsoftware<\/td>\n3<\/td>\nAccess:
\nGaMS-1B | HuggingFace<\/a>\u00a0(The tokenizer is included in the GAMS-1B model, however, it can be downloaded independently; see tokenizer.json<\/a>,\u00a0tokenizer_config.json<\/a>\u00a0and\u00a0special_tokens_map.json<\/a>)<\/td>\n<\/tr>\n
D2.2<\/td>\nOpen-access large generative language model tailored for dialogues and commands with a size of 10 billion parameters.<\/td>\nFRI<\/td>\nsoftware<\/td>\n3<\/td>\nAccess:\u00a0GaMS-27B-Instruct | HuggingFace<\/a> and\u00a0GaMS-27B-Instruct | HuggingFace<\/a><\/td>\n<\/tr>\n
D3.2<\/td>\nCalibrated SloLLaMai models for the humanities and instruction tracking.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n5<\/td>\nAccess:\u00a0Micka-gen3 | HuggingFace<\/a><\/td>\n<\/tr>\n
D4.2<\/td>\nLarge generative language model adapted for the field of medicine.<\/td>\nBetter<\/td>\nsoftware<\/td>\n5<\/td>\nAccess:\u00a0GaMS collection| HuggingFace<\/a>\u00a0(GaMS-2B<\/a>,\u00a0GaMS-9B<\/a>,\u00a0GaMS-27B<\/a>\u00a0\u2013 models pretrained on medical texts corpus (among other corpora) PoVeJMo-VeMo-Med 1.0<\/a>)<\/td>\n<\/tr>\n
August 2025<\/strong><\/td>\n\u00a0<\/strong><\/td>\n<\/tr>\n
D1.6<\/td>\nLarge language corpus for conversational language and addressed terminological areas \u2013 second version.<\/td>\nFRI<\/td>\ndata<\/td>\n4<\/td>\nAccess:<\/p>\n

GaMS-Instruct-MED 2.0 | CLARIN.SI<\/a><\/td>\n<\/tr>\n

D2.3<\/td>\nOpen-access computationally lightweight generative language model tailored for dialogues and commands.<\/td>\nFRI<\/td>\nsoftware<\/td>\n4<\/td>\nAccess:\u00a0GaMS-2B-Instruct | HuggingFace<\/a>\u00a0(GaMS model version which can be run on a basic graphics card on a standard computer)<\/p>\n

Access:\u00a0GaMS-2B-WebGPU | HuggingFace<\/a>\u00a0(GaMS model version, optimized for running online)<\/td>\n<\/tr>\n

D3.3<\/td>\nDemonstration application for OCR.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\nAccess:\u00a0GalisOnline | Description (PDF in Slovene)<\/a><\/td>\n<\/tr>\n
D3.4<\/td>\nDemonstration application for semantic search.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\nAccess:\u00a0Demonstracijska aplikacija za OCR | Description (PDF in Slovene)<\/a><\/td>\n<\/tr>\n
D4.3<\/td>\nPrecise recognizer of Slovenian speech specialized for the field of medicine.<\/td>\nBetter<\/td>\nsoftware<\/td>\n5<\/td>\n <\/td>\n<\/tr>\n
D5.3<\/td>\nOnline service for acoustic preprocessing of audio signals and noise reduction.<\/td>\n\u0160pica<\/td>\nsoftware<\/td>\n5<\/td>\nDescription:\u00a0Spletni servis za akusti\u010dno predprocesiranje zvo\u010dnega signala in odpravo \u0161uma | Description (PDF in Slovene)<\/a>,\u00a0ASR Performance Evaluation Post Speech Enhancement: WER Analysis and Tuning | Attachment 1 (PDF)<\/a>,\u00a0Evaluation of Custom Masking-Based Speech Enhancement and Pretrained NVIDIA BNR Model for Slovenian Language Applications | Attachmet 2 (PDF)<\/a><\/p>\n

Access to the online service:<\/p>\n

Online services<\/a><\/p>\n

API-routes test:<\/p>\n

Swagger<\/a><\/p>\n

Redoc<\/a><\/p>\n

 <\/td>\n<\/tr>\n

D5.4<\/td>\nAccurate and robust multilingual speech recognition model for South Slavic languages.<\/td>\n\u0160pica<\/td>\nsoftware<\/td>\n5<\/td>\nDescription:\u00a0Natan\u010den in robusten ve\u010djezi\u010dni model razpoznave govora za ju\u017enoslovanske jezike | Description (PDF in Slovene)<\/a><\/p>\n

For access contact\u00a0info@vitasis.si<\/a>.<\/td>\n<\/tr>\n

D6.3<\/td>\nRefinement of the plan and corrections to approaches for the effective use of large language models in IaC (Infrastructure as Code): Use and selection of training data, description of approaches in construction.<\/td>\nXLAB<\/td>\ndocumentation<\/td>\n5<\/td>\n\u00a0Description: Dokumentacija in na\u010drt rabe podatkov in pristopov | Description (PDF in Slovene)<\/a><\/td>\n<\/tr>\n
D6.4<\/td>\nSecond version of software enabling the use of language technologies in IaC, taking into account performance, robustness, and security limitations \u2013 achieved TRL5.<\/td>\nXLAB<\/td>\nsoftware<\/td>\n5<\/td>\n\u00a0Description: Druga razli\u010dica programske opreme | Description (PDF in Slovene)<\/a><\/td>\n<\/tr>\n
February 2026<\/strong><\/td>\n\u00a0<\/strong><\/td>\n<\/tr>\n
D1.7<\/td>\nDedicated tokenizers for the Slovenian language \u2013 final version.<\/td>\nFRI<\/td>\nsoftware<\/td>\n4<\/td>\n <\/td>\n<\/tr>\n
D2.4<\/td>\nOpen-access large language model with embedded additional knowledge.<\/td>\nFRI<\/td>\nsoftware<\/td>\n3<\/td>\n <\/td>\n<\/tr>\n
D3.5<\/td>\nDemonstration application for the automatic generation of collection descriptions.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D3.6<\/td>\nDemonstration application for summarizer.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D3.7<\/td>\nDemonstration application for a translator.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D3.8<\/td>\nDemonstration application for translation between instructions in natural language and command language.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D3.9<\/td>\nDevelopment of an application for machine entity extraction and document anonymization, along with a demonstration on databases aquired by Semantika.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n5<\/td>\n <\/td>\n<\/tr>\n
D4.4<\/td>\nMedical application using a speech recognizer and a large generative language model.<\/td>\nBetter<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
June 2026<\/strong><\/td>\n\u00a0<\/strong><\/td>\n<\/tr>\n
D1.8<\/td>\nLarge language corpus for conversational language and addressed terminological areas \u2013 final version.<\/td>\nFRI<\/td>\ndata<\/td>\n4<\/td>\n <\/td>\n<\/tr>\n
D1.9<\/td>\nKnowledge base created based on the Digital Lexical Database.<\/td>\nFRI<\/td>\ndata<\/td>\n3<\/td>\n <\/td>\n<\/tr>\n
D3.10<\/td>\nDemonstration of an upgraded digital guide.<\/td>\nSemantika<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D5.5<\/td>\nPrototype integration of a speech communication system with a selected business process management solution in manufacturing.<\/td>\n\u0160pica<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n
D6.5<\/td>\nFinal version of software enabling the use of language technologies in IaC, taking into account performance, robustness, and security limitations \u2013 achieved TRL6.<\/td>\nXLAB<\/td>\nsoftware<\/td>\n6<\/td>\n <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div><\/section><\/div><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_relevanssi_hide_post":"","_relevanssi_hide_content":"","_relevanssi_pin_for_all":"","_relevanssi_pin_keywords":"","_relevanssi_unpin_keywords":"","_relevanssi_related_keywords":"","_relevanssi_related_include_ids":"","_relevanssi_related_exclude_ids":"","_relevanssi_related_no_append":"","_relevanssi_related_not_related":"","_relevanssi_related_posts":"","_relevanssi_noindex_reason":"","inline_featured_image":false,"episode_type":"","audio_file":"","cover_image":"","cover_image_id":"","duration":"","filesize":"","filesize_raw":"","date_recorded":"","explicit":"","block":"","itunes_episode_number":"","itunes_title":"","itunes_season_number":"","itunes_episode_type":"","footnotes":""},"class_list":["post-948","page","type-page","status-publish","hentry"],"acf":[],"yoast_head":"\nResults - PoVeJMo<\/title>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Results - PoVeJMo\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/\" \/>\n<meta property=\"og:site_name\" content=\"PoVeJMo\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-29T06:46:56+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/\",\"url\":\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/\",\"name\":\"Results - PoVeJMo\",\"isPartOf\":{\"@id\":\"https:\/\/www.cjvt.si\/povejmo\/en\/#website\"},\"datePublished\":\"2020-03-31T20:44:07+00:00\",\"dateModified\":\"2025-09-29T06:46:56+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.cjvt.si\/povejmo\/en\/results\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.cjvt.si\/povejmo\/o-programu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"References\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.cjvt.si\/povejmo\/en\/#website\",\"url\":\"https:\/\/www.cjvt.si\/povejmo\/en\/\",\"name\":\"PoVeJMo\",\"description\":\"Work site\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.cjvt.si\/povejmo\/en\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Results - PoVeJMo","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"en_US","og_type":"article","og_title":"Results - PoVeJMo","og_url":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/","og_site_name":"PoVeJMo","article_modified_time":"2025-09-29T06:46:56+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/","url":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/","name":"Results - PoVeJMo","isPartOf":{"@id":"https:\/\/www.cjvt.si\/povejmo\/en\/#website"},"datePublished":"2020-03-31T20:44:07+00:00","dateModified":"2025-09-29T06:46:56+00:00","breadcrumb":{"@id":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.cjvt.si\/povejmo\/en\/results\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.cjvt.si\/povejmo\/en\/results\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.cjvt.si\/povejmo\/o-programu\/"},{"@type":"ListItem","position":2,"name":"References"}]},{"@type":"WebSite","@id":"https:\/\/www.cjvt.si\/povejmo\/en\/#website","url":"https:\/\/www.cjvt.si\/povejmo\/en\/","name":"PoVeJMo","description":"Work site","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.cjvt.si\/povejmo\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/pages\/948","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/comments?post=948"}],"version-history":[{"count":33,"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/pages\/948\/revisions"}],"predecessor-version":[{"id":1884,"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/pages\/948\/revisions\/1884"}],"wp:attachment":[{"href":"https:\/\/www.cjvt.si\/povejmo\/en\/wp-json\/wp\/v2\/media?parent=948"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}