Commit ·
61bf6ca
1
Parent(s): 7eeef17
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,10 @@ Use this application on HuggingFace🤗 :- https://huggingface.co/spaces/Debasis
|
|
| 14 |
Blog discussing the results :- https://medium.com/@debasishdhaldd99/simplifying-language-through-python-aae6ee7113d9
|
| 15 |
|
| 16 |
This space is aimed at helping people with getting familiarized with Polish, Turkish, Hungarian, Serbo-Croatian-Bosniak (both Latin and Cyrillic based) and Romanian spelling system.
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
| 18 |
properly. This space offers simplified spelling of words/sentence in the said languages. More languages are on the pipeline.
|
| 19 |
|
| 20 |
For example, the Polish word Jarosław, an English speaker who isn't familiar with Polish orthography will pronounce it as Jaroslav, while its actual Polish pronunciation
|
|
@@ -29,16 +32,17 @@ Features added as of now:-
|
|
| 29 |
- Option for the user to generate a random but coherent sentence and pass it as input to the model. Acts as a nice playground for the user.
|
| 30 |
|
| 31 |
# Results in brief
|
|
|
|
| 32 |
|
| 33 |
## Polish
|
| 34 |
Polish spelling => Simplified form
|
| 35 |
|
| 36 |
- Wojciech Szczęsny => Voytsiekh Shensny
|
| 37 |
-
- Grzegorz Krychowiak => Gzhegozh Krykhoviak
|
| 38 |
-
-
|
| 39 |
- Szeleścić => Sheleshtsich
|
| 40 |
|
| 41 |
-
# Hungarian
|
| 42 |
Hungarian spelling => Simplified form
|
| 43 |
|
| 44 |
- Dominik Szoboszlai => Dominik Soboslai
|
|
@@ -46,7 +50,7 @@ Hungarian spelling => Simplified form
|
|
| 46 |
- Debrecen => Debretsen
|
| 47 |
- Pozsony => Pozhony
|
| 48 |
|
| 49 |
-
# Turkish
|
| 50 |
Turkish spelling => Simplified form
|
| 51 |
|
| 52 |
- Azerbaycan => Azerbayjan
|
|
@@ -54,7 +58,7 @@ Turkish spelling => Simplified form
|
|
| 54 |
- Recep Tayyip Erdoğan => Rejep Tayyip Erdo’an
|
| 55 |
- Barış Alper Yılmaz => Barış Alper Yelmaz
|
| 56 |
|
| 57 |
-
# Serbo-Croatian-Bosnian
|
| 58 |
Serbo-Croatian-Bosnian spelling => Simplified form
|
| 59 |
|
| 60 |
- Novak Đoković => Novak Jokovich
|
|
@@ -62,14 +66,14 @@ Serbo-Croatian-Bosnian spelling => Simplified form
|
|
| 62 |
- Edin Džeko => Edin Jeko
|
| 63 |
- Artiljerija => Artilyeriya
|
| 64 |
|
| 65 |
-
# Romanian
|
| 66 |
Romanian spelling => Simplified form
|
| 67 |
|
| 68 |
- Cluj-Napoca => Kluzh Napoka
|
| 69 |
-
- București
|
| 70 |
- Angela Gheorghiu => Anjela Georgiu
|
| 71 |
- Constantin Brâncuși => Konstantin Brunkushi
|
| 72 |
|
| 73 |
|
| 74 |
*************************************************************************************************
|
| 75 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 14 |
Blog discussing the results :- https://medium.com/@debasishdhaldd99/simplifying-language-through-python-aae6ee7113d9
|
| 15 |
|
| 16 |
This space is aimed at helping people with getting familiarized with Polish, Turkish, Hungarian, Serbo-Croatian-Bosniak (both Latin and Cyrillic based) and Romanian spelling system.
|
| 17 |
+
|
| 18 |
+
**Why?**
|
| 19 |
+
|
| 20 |
+
The languages mentioned above, use a modified Latin script with a lot of diacritic marks and digraphs, thus often making them difficult for non-native speakers to pronounce or read the words
|
| 21 |
properly. This space offers simplified spelling of words/sentence in the said languages. More languages are on the pipeline.
|
| 22 |
|
| 23 |
For example, the Polish word Jarosław, an English speaker who isn't familiar with Polish orthography will pronounce it as Jaroslav, while its actual Polish pronunciation
|
|
|
|
| 32 |
- Option for the user to generate a random but coherent sentence and pass it as input to the model. Acts as a nice playground for the user.
|
| 33 |
|
| 34 |
# Results in brief
|
| 35 |
+
For each language, some names/placenames in that language were given to this web app as input, the simplified outputs are presented below.
|
| 36 |
|
| 37 |
## Polish
|
| 38 |
Polish spelling => Simplified form
|
| 39 |
|
| 40 |
- Wojciech Szczęsny => Voytsiekh Shensny
|
| 41 |
+
- Grzegorz Krychowiak => Gzhegozh Krykhoviak (zh is pronounced like the "s" in measure/vision)
|
| 42 |
+
- Łódź => Wuj
|
| 43 |
- Szeleścić => Sheleshtsich
|
| 44 |
|
| 45 |
+
## Hungarian
|
| 46 |
Hungarian spelling => Simplified form
|
| 47 |
|
| 48 |
- Dominik Szoboszlai => Dominik Soboslai
|
|
|
|
| 50 |
- Debrecen => Debretsen
|
| 51 |
- Pozsony => Pozhony
|
| 52 |
|
| 53 |
+
## Turkish
|
| 54 |
Turkish spelling => Simplified form
|
| 55 |
|
| 56 |
- Azerbaycan => Azerbayjan
|
|
|
|
| 58 |
- Recep Tayyip Erdoğan => Rejep Tayyip Erdo’an
|
| 59 |
- Barış Alper Yılmaz => Barış Alper Yelmaz
|
| 60 |
|
| 61 |
+
## Serbo-Croatian-Bosnian
|
| 62 |
Serbo-Croatian-Bosnian spelling => Simplified form
|
| 63 |
|
| 64 |
- Novak Đoković => Novak Jokovich
|
|
|
|
| 66 |
- Edin Džeko => Edin Jeko
|
| 67 |
- Artiljerija => Artilyeriya
|
| 68 |
|
| 69 |
+
## Romanian
|
| 70 |
Romanian spelling => Simplified form
|
| 71 |
|
| 72 |
- Cluj-Napoca => Kluzh Napoka
|
| 73 |
+
- București => Bukureshti (Bucharest)
|
| 74 |
- Angela Gheorghiu => Anjela Georgiu
|
| 75 |
- Constantin Brâncuși => Konstantin Brunkushi
|
| 76 |
|
| 77 |
|
| 78 |
*************************************************************************************************
|
| 79 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|