| dc.contributor.author | Žgank, Andrej |
| dc.contributor.author | Verdonik, Darinka |
| dc.contributor.author | Boto, Sanja |
| dc.contributor.author | Donaj, Gregor |
| dc.date.accessioned | 2026-09-14T16:29:21Z |
| dc.date.available | 2026-09-14T16:29:21Z |
| dc.date.issued | 2026-08-31 |
| dc.identifier.uri | http://hdl.handle.net/11356/2484 |
| dc.description | This resource provides automatic speech recognition (ASR) models for the Slovenian Gail Valley dialect, developed using the open-source WeNet 3.1 framework. The models were trained on 84.25 hours of speech from the Corpus of the Gail Valley dialect Zila 1.0 (http://hdl.handle.net/11356/2257). The system employs a hybrid CTC/attention architecture with a Conformer encoder and Transformer decoder. The log-Mel filterbank features were used for training. The final averaged model achieves a word error rate of 24.64% and a character error rate of 12.05%. Models are provided in WeNet and ONNX formats, supporting local, server-based, and GPU-accelerated inference and deployment. |
| dc.language.iso | slv |
| dc.publisher | University of Maribor, Faculty of Electrical Engineering and Computer Science |
| dc.publisher | Mohorjeva družba / Hermagoras Verein |
| dc.relation.isreferencedby | https://doi.org/10.63317/3fhhk948chhm |
| dc.rights | Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/4.0/ |
| dc.rights.label | PUB |
| dc.source.uri | https://lingua.mohorjeva.at/zila-digital-zila-digital |
| dc.subject | automatic speech recognition |
| dc.subject | dialect |
| dc.title | Gail Valley dialect E2E Automatic Speech Recognition model Zila 1.0 |
| dc.type | toolService |
| metashare.ResourceInfo#ContentInfo.detailedType | tool |
| metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
| has.files | yes |
| branding | CLARIN.SI data & tools |
| contact.person | Andrej Zgank andrej.zgank@um.si University of Maribor, Faculty of Electrical Engineering and Computer Science |
| sponsor | European Regional Development Fund within the framework of the Interreg Slovenia–Austria Programme 2021–2027 and the State of Carinthia SI-AT00017, ATU25358305 INTERREG-Projekt "LINGUA" SI-AT00017 Other |
| files.count | 1 |
| files.size | 548440202 |
Datoteke v tem vnosu
To je vnos
Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Publicly Available
z licenco:Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
- Ime
- ZilaASRmodels.zip
- Velikost
- 523.03 MB
- Format
- application/zip
- Opis
- Gail Valley ASR models Zila
- MD5
- 88d4b29235102acd02ddf3ea2159e8e4
- ZilaASRmodels
- copyright.txt401 B
- Doc
- Zila-ASR-DOC_v1.0.pdf248 kB
- readme.txt1 kB
- Zila-runtime
- copyright.txt401 B
- final.zip188 MB
- train_units.txt68 kB
- Zila-ONNX
- train.yaml1 kB
- copyright.txt401 B
- onnx-gpu-model
- config.yaml64 B
- decoder.onnx51 MB
- encoder.onnx137 MB
- global_cmvn2 kB
- train_unigram.model318 kB
- train_units.txt68 kB
- Zila-devel
- train.yaml1 kB
- copyright.txt401 B
- avg_10.pt188 MB
- global_cmvn2 kB
- train_unigram.model318 kB
- train_units.txt68 kB