read double digits for telephone grammar (#32)

* read double digits for telephone grammar

Signed-off-by: Larisa Kempbell <lkempbell@nvidia.com>

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

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

* import zero graph instead of hard coding

Signed-off-by: Larisa Kempbell <lkempbell@nvidia.com>

---------

Signed-off-by: Larisa Kempbell <lkempbell@nvidia.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: LarisaKe

nemo_text_processing/inverse_text_normalization/fr/taggers/telephone.py

@@ -52,17 +52,36 @@ def __init__(self):
             (graph_ties + delete_hyphen + graph_digit),
         )
 
+        # accept `double zéro` -> `00`
+        single_digits = graph_digit | graph_zero
+        digit_words = pynini.union(graph_digit.optimize(), graph_zero).invert()
+
+        doubled_digit = pynini.union(
+            *[
+                pynini.cross(
+                    pynini.project(str(i) @ digit_words, "output")
+                    + pynini.accep(" ")
+                    + pynini.project(str(i) @ digit_words, "output"),
+                    pynutil.insert("double ") + pynini.project(str(i) @ digit_words, "output"),
+                )
+                for i in range(10)
+            ]
+        )
+        doubled_digit.invert()
+        digit_twice = single_digits + pynutil.delete(" ") + single_digits
+        doubled_digit @= digit_twice
+
         graph_first_pair = graph_zero + delete_space + graph_digit
         graph_first_pair |= pynutil.insert("0") + graph_digit  # if zero is omitted
+        graph_first_pair |= doubled_digit
         graph_first_pair += (
             delete_space + insert_space
         )  # delete_space since closure allows possible gaps to be removed
 
         # All digits
-        single_digits = graph_digit | graph_zero
-
         graph_pair_all_digits = single_digits + delete_space
         graph_pair_all_digits += single_digits
+        graph_pair_all_digits |= doubled_digit
 
         graph_all_digits = pynini.closure(graph_pair_all_digits + delete_space + insert_space, 3, 3)
         graph_all_digits = graph_first_pair + graph_all_digits + graph_pair_all_digits

tests/nemo_text_processing/fr/data_inverse_text_normalization/test_cases_telephone.txt

@@ -1,4 +1,5 @@
 zéro deux douze trente-deux trente trente~02 12 32 30 30
 zéro deux une deux trois deux trois zéro trois zéro~02 12 32 30 30
 deux douze trente-deux trente trente~02 12 32 30 30
-deux une deux trois deux trois zéro trois zéro~02 12 32 30 30
+deux une deux trois deux trois zéro trois zéro~02 12 32 30 30
+double neuf douze trente-deux trente trente~99 12 32 30 30