Skip to content

Add Kannada (kn-IN) G2P support for TTS #15582

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jasro23 wants to merge 2 commits into
base: main
Choose a base branch
from
+4,948 −1
Open

Add Kannada (kn-IN) G2P support for TTS #15582

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8ddb3c2
Add Kannada (kn-IN) G2P support for TTS
jasro23 Mar 18, 2026
aa14c48
Apply isort and black reformatting
jasro23 Apr 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 58 additions & 1 deletion nemo/collections/common/tokenizers/text_to_speech/ipa_lexicon.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@

# fmt: off

SUPPORTED_LOCALES = ["en-US", "de-DE", "es-ES", "it-IT", "fr-FR", "vi-VN", "ja-JP", "hi-IN"]
SUPPORTED_LOCALES = ["en-US", "de-DE", "es-ES", "it-IT", "fr-FR", "vi-VN", "ja-JP", "hi-IN", "kn-IN"]

DEFAULT_PUNCTUATION = (
',', '.', '!', '?', '-',
Expand Down Expand Up @@ -107,6 +107,31 @@
# Danda (period)
'।',
),
"kn-IN": (
# Independent Vowels (Swaras)
'ಅ', 'ಆ', 'ಇ', 'ಈ', 'ಉ', 'ಊ', 'ಋ', 'ೠ', 'ಌ', 'ೡ',
'ಎ', 'ಏ', 'ಐ', 'ಒ', 'ಓ', 'ಔ',
# Consonants (Vyanjanas)
# Velar
'ಕ', 'ಖ', 'ಗ', 'ಘ', 'ಙ',
# Palatal
'ಚ', 'ಛ', 'ಜ', 'ಝ', 'ಞ',
# Retroflex
'ಟ', 'ಠ', 'ಡ', 'ಢ', 'ಣ',
# Dental
'ತ', 'ಥ', 'ದ', 'ಧ', 'ನ',
# Labial
'ಪ', 'ಫ', 'ಬ', 'ಭ', 'ಮ',
# Approximants and others
'ಯ', 'ರ', 'ಱ', 'ಲ', 'ಳ', 'ೞ', 'ವ', 'ಶ', 'ಷ', 'ಸ', 'ಹ',
# Dependent Vowel Signs (Matras)
'ಾ', 'ಿ', 'ೀ', 'ು', 'ೂ', 'ೃ', 'ೄ', 'ೆ', 'ೇ', 'ೈ', 'ೊ', 'ೋ', 'ೌ',
# Various Signs
'ಂ', # Anusvara
'ಃ', # Visarga
'್', # Virama (Halant)
'ಽ', # Avagraha
),
}

IPA_CHARACTER_SETS = {
Expand Down Expand Up @@ -183,6 +208,30 @@
'ɡ', 'ɣ', 'ɪ', 'ɭ', 'ɲ', 'ɳ', 'ɾ', 'ʂ', 'ʃ', 'ʈ',
'ʊ', 'ʋ', 'ʌ', 'ʰ', 'ː', '̃', '̩', 'χ',
),
# Kannada IPA phoneme set (split form - all modifiers as separate tokens)
"kn-IN": (
# Vowels (monophthongs) - base forms only
'a', 'i', 'u', 'e', 'o',
'ə', # schwa (inherent vowel, sometimes realized)
'ɯ', # close back unrounded vowel (for vocalic R: ಋ, ೃ)
# Consonants - Stops (base forms only)
'k', 'g', # Velar
'ʈ', 'ɖ', # Retroflex
't', 'd', # Dental
'p', 'b', # Labial
# Nasals
'ŋ', 'ɲ', 'ɳ', 'n', 'm',
# Approximants
'j', 'ʋ', 'w',
# Liquids
'r', 'ɾ', 'l', 'ɭ', 'ɻ',
# Fricatives/Affricates (ʃ, ʒ used in affricates tʃ, dʒ)
'ʃ', 'ʒ', 'ʂ', 's', 'h',
# Modifiers (separate tokens, like Hindi/Japanese)
'ʰ', # Aspiration marker
'ː', # Length marker
'̃', # Nasalization (combining tilde)
),
}

GRAPHEME_CHARACTER_CASES = ["upper", "lower", "mixed"]
Expand Down Expand Up @@ -347,5 +396,13 @@ def get_ipa_punctuation_list(locale):
'・',
]
)
elif locale == "kn-IN":
# Kannada punctuation
punct_set.update(
[
'।', # Devanagari Danda (single)
'॥', # Devanagari Double Danda
]
)
punct_list = sorted(list(punct_set))
return punct_list
Loading
Loading