INFO_MAIN= " Welcome to the Polish ASR Survey dashboard!
\
You can use this dashboard to learn about the state of Polish ASR speech data and benchmarks.
\
The dashboard is built upon the [*Polish ASR Speech Datasets Catalog*](https://github.com/goodmike31/pl-asr-speech-data-survey) and [*Polish ASR Benchmarks Catalog*](https://docs.google.com/spreadsheets/d/1fVsE98Ulmt-EIEe4wx8sUdo7RLigDdAVjQxNpAJIrH8/edit?usp=sharing).
\
The dashboard is divided into the following tabs:
\
* **About Polish ASR Survey** - general information about the survey, references, and contact points
\
* **Polish ASR Speech Data Catalog** - detailed information about the speech data available for Polish ASR
\
* **Polish ASR Speech Data Survey** - analysis of the state of Polish ASR speech data
\
* **ASR Speech Data Taxonomy** - explanation of the columns in the *Polish ASR Speech Datasets Catalog*
\
* **Polish ASR Benchmarks Catalog** - detailed information about the benchmarks available for Polish ASR
\
* **Polish ASR Benchmarks Survey** - analysis of the state of Polish ASR benchmarks
\
* **ASR Benchmarks Taxonomy** - explanation of the columns in the *Polish ASR Benchmarks Catalog*
\
Please visit respective tab to learn how to use it and provide feedback.
\
If you want to share your feedback regarding the Speech Data catalog, please use this [FORM](https://forms.gle/EWJ6YfbJJTyEzQs66).
\
If you are looking for the latest ASR benchmarks for Polish, please visit the [BIGOS/PELCRA ASR leaderboard](https://huggingface.co/spaces/amu-cai/pl-asr-bigos-bench-dash).
\
You can also contact the author via [email](mailto:michal.junczyk@amu.edu.pl) or [LinkedIn](https://www.linkedin.com/in/michaljunczyk/).
"
CITATION_MAIN = "@misc{junczyk-2024-pl-asr-survey
\
title = {Polish ASR Survey},
\
author = {Michał Junczyk},
\
year = {2024},
\
publisher = {Hugging Face},
\
url = {https://huggingface.co/spaces/amu-cai/pl-asr-survey} }"
# TODO
# * Analysis of datasets utility for the purpose of ASR evaluation (see the **Dataset Utility Index** tab)
\
############################################################################################################
INFO_CATALOG= "This dashboard complements *Polish ASR Speech Datasets Catalog* available on [GitHub](https://github.com/goodmike31/pl-asr-speech-data-survey) and [Google Sheets](https://docs.google.com/spreadsheets/d/181EDfwZNtHgHFOMaKNtgKssrYDX4tXTJ9POMzBsCRlI/edit#gid=0) by providing:
\
* More convenient browsing of the catalog content (*see the **How to use?** section below*)
\
* Up-to-data analysis of the state of Polish ASR speech data (*see the **Polish ASR Speech Data Survey** tab*)
\
IMPORTANT - If you want to share your feedback regarding the catalog, please use this [FORM](https://forms.gle/EWJ6YfbJJTyEzQs66). Each response is granted 50 PLN for the charity of your choice.
\
Your feedback will be helpful to assess the state of Polish ASR speech data from the community perspective.
\
If you want report missing dataset or request correction of descriptons, please follow the steps described on [GitHub](https://github.com/goodmike31/pl-asr-speech-data-survey?tab=readme-ov-file#how-to-contribute-to-the-polish-asr-speech-datasets-catalog)
\
You can also contact the author via [email](mailto:michal.junczyk@amu.edu.pl) or [LinkedIn](https://www.linkedin.com/in/michaljunczyk/).
"
CITATION_CATALOG="@article{Junczyk+2024+27+52,
\
url = {https://doi.org/10.1515/psicl-2023-0019},
\
title = {A survey of Polish ASR speech datasets},
\
author = {Michał Junczyk},
\
pages = {27--52},
\
volume = {60},
\
number = {1},
\
journal = {Poznan Studies in Contemporary Linguistics},
\
doi = {doi:10.1515/psicl-2023-0019},
\
year = {2024},
\
lastchecked = {2024-03-10}
\
}"
HOWTO_CATALOG = "To browse the catalog content using filters you must enable them first.
\
You can also sort the columns by clicking on the column header.
\
Depending on the column type, you can use the search box to filter the content.
\
Please refer to the **ASR Speech Data Taxonomy** tab for the explanation of the columns.
\
If you looking for insights derived from the collected in the catalog, please go to **Polish ASR Speech Data Survey** tab.
"
HOWTO_TAXONOMY_CAT = "This table presents descriptors (columns) used in the *Polish ASR Speech Datasets Catalog*
\
Taxonomy is also provided on [GitHub as TSV file](https://github.com/goodmike31/pl-asr-speech-data-survey/blob/main/snapshots/pl-asr-speech-datasets-catalog-latest.tsv) and [Google Sheets](https://docs.google.com/spreadsheets/d/181EDfwZNtHgHFOMaKNtgKssrYDX4tXTJ9POMzBsCRlI/edit#gid=2015613057)"
############################################################################################################
INFO_BENCHMARK = "TODO"
CITATION_BENCHMARK="@misc{junczyk-2023-pl-asr-speech-data-catalog,
\
title = {Polish ASR Speech Datasets Catalog},
\
author = {Michał Junczyk},
\
year = {2023},
\
publisher = {Github},
\
url = {https://github.com/goodmike31/pl-asr-speech-data-survey} }"
HOWTO_BENCHMARK = "You can use the filters to browse the catalog content.
\
You can also sort the columns by clicking on the column header.
\
Depending on the column type, you can use the search box to filter the content.
\
Please refer to the **ASR Benchmarks Catalog Taxonomy** tab for the explanation of the columns.
"
############################################################################################################