ES TN Fix for Issue #166 (#224)

* ES TN Fix for Issue #166

Signed-off-by: Simon Zuberek <szuberek@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Updates the cache

Signed-off-by: Simon Zuberek <szuberek@nvidia.com>

* Unioning the lower and upper Roman graphs into one

Signed-off-by: Simon Zuberek <szuberek@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Removes all upper-case Roman numerals from data files

Signed-off-by: Simon Zuberek <szuberek@nvidia.com>

---------

Signed-off-by: Simon Zuberek <szuberek@nvidia.com>
Co-authored-by: Simon Zuberek <szuberek@nvidia.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Alex Cui <alexcui1994@gmail.com>

Jenkinsfile

@@ -13,8 +13,13 @@ pipeline {
 
     AR_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/04-24-24-0'
     DE_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/06-03-24-0'
+<<<<<<< HEAD
     EN_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/09-04-24-0'
     ES_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/09-25-24-0'
+=======
+    EN_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/08-22-24-0'
+    ES_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/08-30-24-0'
+>>>>>>> 208d055 (ES TN Fix for Issue #166 (#224))
     ES_EN_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/08-30-24-0'
     FR_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/06-04-24-0'
     HU_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/07-16-24-0'

nemo_text_processing/text_normalization/es/data/ordinals/roman_exceptions.tsv

@@ -7,4 +7,8 @@ x
 l
 c
 d
+<<<<<<< HEAD
 m
+=======
+m
+>>>>>>> 208d055 (ES TN Fix for Issue #166 (#224))

nemo_text_processing/text_normalization/es/graph_utils.py

@@ -44,11 +44,7 @@
 ES_PLUS = pynini.union("más", "Más", "MÁS").optimize()
 
 
-<<<<<<< HEAD
 def strip_accent(fst: "pynini.FstLike") -> "pynini.FstLike":
-=======
-def strip_accent(fst: 'pynini.FstLike') -> 'pynini.FstLike':
->>>>>>> a8ca196 (es and es_en changes for unified models (#143))
     """
     Converts all accented vowels to non-accented equivalents
 
@@ -216,4 +212,4 @@ def _load_roman(file: str, upper_casing: bool):
         )
     ).optimize()
 
-    return graph @ fst
+    return graph @ fst

tests/nemo_text_processing/es/data_text_normalization/test_cases_ordinal.txt

@@ -117,4 +117,4 @@ todo mi reconocimiento~todo mi reconocimiento
 V~quinto
 El texto de Li Qin en este libro ahora está disponible en forma de libro electrónico.~El texto de Li Qin en este libro ahora está disponible en forma de libro electrónico.
 Xi Jinping es el actual presidente de China.~Xi Jinping es el actual presidente de China.
-Matías fue el XI apóstol.~Matías fue el undécimo apóstol.
+Matías fue el XI apóstol.~Matías fue el undécimo apóstol.