Punjabi CV dictionary v2.0.0#
@misc{Ahn_Chodroff_2022,
author={Ahn, Emily and Chodroff, Eleanor},
title={VoxCommunis Corpus},
address={\url{https://osf.io/t957v}},
publisher={OSF},
year={2022},
month={Jan}
}
|
Installation#
Install from the MFA command line:
mfa model download dictionary punjabi_cv
Or download from the release page.
Intended use#
This dictionary is intended for forced alignment of Punjabi transcripts.
This dictionary uses the Epitran phone set for Punjabi, and was used in training the Punjabi Epitran acoustic model. Pronunciations can be added on top of the dictionary, as long as no additional phones are introduced.
Performance Factors#
When trying to get better alignment accuracy, adding pronunciations is generally helpful, especially for different styles and dialects. The most impactful improvements will generally be seen when adding reduced variants that involve deleting segments/syllables common in spontaneous speech. Alignment must include all phones specified in the pronunciation of a word, and each phone has a minimum duration (by default 10ms). If a speaker pronounces a multisyllabic word with just a single syllable, it can be hard for MFA to fit all the segments in, so it will lead to alignment errors on adjacent words as well.
Ethical considerations#
Deploying any Speech-to-Text model into any production setting has ethical implications. You should consider these implications before use.
Demographic Bias#
You should assume every machine learning model has demographic bias unless proven otherwise. For pronunciation dictionaries, it is often the case that transcription accuracy and lexicon coverage for the prestige variety modeled in this dictionary compared to other variants. If you are using this dictionary in production, you should acknowledge this as a potential issue.
IPA Charts#
Consonants#
Obstruent symbols to the left of are unvoiced and those to the right are voiced.
Manner |
Labial |
Labiodental |
Dental |
Alveolar |
Alveopalatal |
Retroflex |
Palatal |
Velar |
Glottal |
---|---|---|---|---|---|---|---|---|---|
Nasal |
Occurrences: 471 Examples: * ਮੋਅ: [m o] * ਮਿਸਾਲ: [m ɪ s ɑ l] * ਮਸਲੇ: [m ə s l e] * ਮਾੜਾ: [m ɑ ɽ ɑ] Occurrences: 1 Examples: * ਸੁਖੱਮ: [s ʊ kʰ ə mː] |
Occurrences: 468 Examples: * ਨਸਲ: [n ə s ə l] * ਚਾਨਣ: [t͡ʃ ɑ n ə ɳ] * ਇਹਨੂੰ: [ɪ ɦ n ũ] * ਜ਼ਨਾਨੀ: [z ə n ɑ n i] |
Occurrences: 210 Examples: * ਚਾਨਣ: [t͡ʃ ɑ n ə ɳ] * ਕਹਿਣ: [k ə ɦ ɪ ɳ] * ਬਣੀ: [b ə ɳ i] * ਜਗਾਉਣ: [d͡ʒ ə ɡ ɑ ʊ ɳ] Occurrences: 1 Examples: * ਬੱਣਾਈ: [b ə ɳː ɑ i] |
||||||
Stop |
Occurrences: 413 Examples: * ਭਗਤ: [p ə ɡ ə t̪] * ਪੱਤਰ: [p ə t̪ː ə ɾ] * ਪੱਕ: [p ə kː] * ਪੱਕੀ: [p ə kː i] Occurrences: 14 Examples: * ਡੱਫੀ: [ɖ ə pː i] * ਉੱਪਰ: [ʊ pː ə ɾ] * ਸੱਭ: [s ə pː] * ਥੱਪੜ: [t̪ʰ ə pː ə ɽ] Occurrences: 318 Examples: * ਬਰੰਗੇ: [b ə ɾ ə̃ ɡ e] * ਅਜੀਬ: [ə d͡ʒ i b] * ਬਣੀ: [b ə ɳ i] * ਬੈਠੋ: [b ɛ ʈʰ o] Occurrences: 10 Examples: * ਪੱਬ: [p ə bː] * ਡੱਬੀ: [ɖ ə bː i] * ਬੱਬਰ: [b ə bː ə ɾ] * ਰੱਬਾ: [ɾ ə bː ɑ] |
Occurrences: 475 Examples: * ਭਗਤ: [p ə ɡ ə t̪] * ਤੜਕੇ: [t̪ ə ɽ k e] * ਆਤਮਾ: [ɑ t̪ m ɑ] * ਖੋਤੇ: [kʰ o t̪ e] Occurrences: 62 Examples: * ਪੱਤਰ: [p ə t̪ː ə ɾ] * ਦਿੱਤਾ: [d̪ ɪ t̪ː ɑ] * ਸੁੱਤਾ: [s ʊ t̪ː ɑ] * ਸਿੱਧੀ: [s ɪ t̪ː i] Occurrences: 478 Examples: * ਸੰਦੜਾ: [s ə̃ d̪ ə ɽ ɑ] * ਸ਼ਾਇਦ: [ʃ ɑ ɪ d̪] * ਸੰਦੇਸ਼: [s ə̃ d̪ e ʃ] * ਰਖਦਾ: [ɾ ə kʰ d̪ ɑ] Occurrences: 10 Examples: * ਮੁੱਦਾ: [m ʊ d̪ː ɑ] * ਸੱਦਣਾ: [s ə d̪ː ə ɳ ɑ] * ਸਰਹੱਦ: [s ə ɾ ɦ ə d̪ː] * ਸੱਦਾਮ: [s ə d̪ː ɑ m] |
Occurrences: 190 Examples: * ਛੋਟੀ: [t͡ʃʰ o ʈ i] * ਸਟੀਕ: [s ə ʈ i k] * ਲੌਢਾ: [l ɔ ʈ ɑ] * ਗੇਟ: [ɡ e ʈ] Occurrences: 39 Examples: * ਪਿੱਠ: [p ɪ ʈː] * ਹੱਟੀ: [ɦ ə ʈː i] * ਰੱਟੇ: [ɾ ə ʈː e] * ਗੱਠੇ: [ɡ ə ʈː e] Occurrences: 117 Examples: * ਸਾਡਾ: [s ɑ ɖ ɑ] * ਡੈਡੀ: [ɖ ɛ ɖ i] * ਤਾਂਡਵ: [t̪ ɑ̃ ɖ ə ʋ] * ਕਾਰਡ: [k ɑ ɾ ə ɖ] Occurrences: 19 Examples: * ਕਬੱਡੀ: [k ə b ə ɖː i] * ਛੱਡ: [t͡ʃʰ ə ɖː] * ਉੱਡ: [ʊ ɖː] * ਲੱਡੂ: [l ə ɖː u] |
Occurrences: 557 Examples: * ਅੰਕੜੇ: [ə̃ k ə ɽ e] * ਕਹਿਣ: [k ə ɦ ɪ ɳ] * ਤੜਕੇ: [t̪ ə ɽ k e] * ਫਰਕ: [pʰ ə ɾ ə k] Occurrences: 86 Examples: * ਲੁੱਕ: [l ʊ kː] * ਪੱਕ: [p ə kː] * ਪੱਕੀ: [p ə kː i] * ਹਿੱਕ: [ɦ ɪ kː] Occurrences: 277 Examples: * ਭਗਤ: [p ə ɡ ə t̪] * ਬਰੰਗੇ: [b ə ɾ ə̃ ɡ e] * ਜਗਾਉਣ: [d͡ʒ ə ɡ ɑ ʊ ɳ] * ਚੰਗਾ: [t͡ʃ ə̃ ɡ ɑ] Occurrences: 20 Examples: * ਲੱਗੀ: [l ə ɡː i] * ਅੱਗੇ: [ə ɡː e] * ਪੱਗ: [p ə ɡː] * ਅਲੱਗ: [ə l ə ɡː] |
|||||
Affricate |
Occurrences: 194 Examples: * ਚੋਰ: [t͡ʃ o ɾ] * ਚਾਨਣ: [t͡ʃ ɑ n ə ɳ] * ਚੰਗਾ: [t͡ʃ ə̃ ɡ ɑ] * ਚੌਕਸੀ: [t͡ʃ ɔ k s i] Occurrences: 28 Examples: * ਉੱਚਾ: [ʊ t͡ʃː ɑ] * ਮੱਚਿਆ: [m ə t͡ʃː ɪ ɑ] * ਇੱਛਾ: [ɪ t͡ʃː ɑ] * ਨੱਚਦਾ: [n ə t͡ʃː ə d̪ ɑ] Occurrences: 249 Examples: * ਰਜਾ: [ɾ ə d͡ʒ ɑ] * ਅਜੀਬ: [ə d͡ʒ i b] * ਜਗਾਉਣ: [d͡ʒ ə ɡ ɑ ʊ ɳ] * ਜਾਣ: [d͡ʒ ɑ ɳ] Occurrences: 10 Examples: * ਕੁੱਜੇ: [k ʊ d͡ʒː e] * ਭੱਜ: [p ə d͡ʒː] * ਵੱਜ: [ʋ ə d͡ʒː] * ਅੱਜ: [ə d͡ʒː] |
||||||||
Sibilant |
Occurrences: 542 Examples: * ਨਸਲ: [n ə s ə l] * ਸੰਦੜਾ: [s ə̃ d̪ ə ɽ ɑ] * ਸਾਡਾ: [s ɑ ɖ ɑ] * ਵਸਾਹ: [ʋ ə s ɑ ɦ] Occurrences: 14 Examples: * ਹੱਸ: [ɦ ə sː] * ਦੱਸ: [d̪ ə sː] * ਜੱਸੀ: [d͡ʒ ə sː i] * ਜੁੱਸਾ: [d͡ʒ ʊ sː ɑ] Occurrences: 82 Examples: * ਜ਼ਨਾਨੀ: [z ə n ɑ n i] * ਨਜ਼ਰੀਂ: [n ə z ɾ ĩ] * ਜਹਾਜ਼: [d͡ʒ ə ɦ ɑ z] * ਜ਼ਰੂਰ: [z ə ɾ u ɾ] |
Occurrences: 165 Examples: * ਸ਼ਾਇਦ: [ʃ ɑ ɪ d̪] * ਸੰਦੇਸ਼: [s ə̃ d̪ e ʃ] * ਫੈਸ਼ਨ: [pʰ ɛ ʃ ə n] * ਸ਼ੋਰੀ: [ʃ o ɾ i] Occurrences: 2 Examples: * ਬੁੱਸ਼: [b ʊ ʃː] * ਸਪੱਸ਼ਟ: [s ə p ə ʃː ə ʈ] |
|||||||
Fricative |
Occurrences: 35 Examples: * ਤਫ਼ਸੀਲ: [t̪ ə f s i l] * ਫ਼ਤਹਿ: [f ə t̪ ɦ ɪ] * ਸੈਫ਼: [s ɛ f] * ਸਫ਼ਰ: [s ə f ə ɾ] |
Occurrences: 436 Examples: * ਕਹਿਣ: [k ə ɦ ɪ ɳ] * ਵਸਾਹ: [ʋ ə s ɑ ɦ] * ਇਹਨੂੰ: [ɪ ɦ n ũ] * ਹੋਇਆ: [ɦ o ɪ ɑ] Occurrences: 1 Examples: * ਇੱਹ: [ɪ ɦː] |
|||||||
Approximant |
Occurrences: 334 Examples: * ਵਸਾਹ: [ʋ ə s ɑ ɦ] * ਵਸੀਲੇ: [ʋ ə s i l e] * ਨਵਨੀਤ: [n ə ʋ n i t̪] * ਦੀਵੇ: [d̪ i ʋ e] Occurrences: 2 Examples: * ਅੱਵਲ: [ə ʋː ə l] |
Occurrences: 27 Examples: * ਯਤਨਾਂ: [j ə t̪ n ɑ̃] * ਯਾਤਰੀ: [j ɑ t̪ ɾ i] * ਯੋਧੇ: [j o t̪ e] * ਯਕੀਨਨ: [j ə k i n ə n] |
|||||||
Tap |
Occurrences: 1,017 Examples: * ਚੋਰ: [t͡ʃ o ɾ] * ਰਜਾ: [ɾ ə d͡ʒ ɑ] * ਬਰੰਗੇ: [b ə ɾ ə̃ ɡ e] * ਫਰਕ: [pʰ ə ɾ ə k] |
Occurrences: 127 Examples: * ਅੰਕੜੇ: [ə̃ k ə ɽ e] * ਸੰਦੜਾ: [s ə̃ d̪ ə ɽ ɑ] * ਤੜਕੇ: [t̪ ə ɽ k e] * ਮਾੜਾ: [m ɑ ɽ ɑ] |
|||||||
Lateral |
Occurrences: 520 Examples: * ਨਸਲ: [n ə s ə l] * ਮਿਸਾਲ: [m ɪ s ɑ l] * ਮਸਲੇ: [m ə s l e] * ਲੁੱਕ: [l ʊ kː] Occurrences: 42 Examples: * ਬਿੱਲੂ: [b ɪ lː u] * ਕੁੱਲ: [k ʊ lː] * ਅਭੁੱਲ: [ə p ʊ lː] * ਚੱਲਦੀ: [t͡ʃ ə lː ə d̪ i] |
||||||||
Lateral Tap |
Occurrences: 6 Examples: * ਨਾਲ਼: [n ɑ ɭ] * ਭਾਲ਼: [p ɑ ɭ] * ਕੋਲ਼: [k o ɭ] * ਵਾਲ਼ੀ: [ʋ ɑ ɭ i] |
Vowels#
Vowel symbols to the left of are unrounded and those to the right are rounded.
Oral Vowels#
Front |
Near-Front |
Central |
Near-Back |
Back |
|
---|---|---|---|---|---|
Close |
Occurrences: 799 Examples: * ਅਜੀਬ: [ə d͡ʒ i b] * ਬਣੀ: [b ə ɳ i] * ਵਸੀਲੇ: [ʋ ə s i l e] * ਗੁਈ: [ɡ ʊ i] |
Occurrences: 125 Examples: * ਬਿੱਲੂ: [b ɪ lː u] * ਦੂਸ਼ਿਤ: [d̪ u ʃ ɪ t̪] * ਜਾਣੂ: [d͡ʒ ɑ ɳ u] * ਮਜਬੂਰ: [m ə d͡ʒ b u ɾ] |
|||
Occurrences: 683 Examples: * ਕਹਿਣ: [k ə ɦ ɪ ɳ] * ਮਿਸਾਲ: [m ɪ s ɑ l] * ਇਹਨੂੰ: [ɪ ɦ n ũ] * ਸ਼ਾਇਦ: [ʃ ɑ ɪ d̪] |
Occurrences: 384 Examples: * ਲੁੱਕ: [l ʊ kː] * ਜਗਾਉਣ: [d͡ʒ ə ɡ ɑ ʊ ɳ] * ਗੁਈ: [ɡ ʊ i] * ਉਦਾਸ: [ʊ d̪ ɑ s] |
||||
Close-Mid |
Occurrences: 584 Examples: * ਅੰਕੜੇ: [ə̃ k ə ɽ e] * ਬਰੰਗੇ: [b ə ɾ ə̃ ɡ e] * ਤੜਕੇ: [t̪ ə ɽ k e] * ਮਸਲੇ: [m ə s l e] |
Occurrences: 289 Examples: * ਮੋਅ: [m o] * ਚੋਰ: [t͡ʃ o ɾ] * ਹੋਇਆ: [ɦ o ɪ ɑ] * ਰਸੋਈ: [ɾ ə s o i] |
|||
Occurrences: 1,822 Examples: * ਅੰਕੜੇ: [ə̃ k ə ɽ e] * ਨਸਲ: [n ə s ə l] * ਭਗਤ: [p ə ɡ ə t̪] * ਰਜਾ: [ɾ ə d͡ʒ ɑ] |
|||||
Open-Mid |
Occurrences: 130 Examples: * ਬੈਠੋ: [b ɛ ʈʰ o] * ਫੈਸ਼ਨ: [pʰ ɛ ʃ ə n] * ਬੈਨਰ: [b ɛ n ə ɾ] * ਡੈਡੀ: [ɖ ɛ ɖ i] |
Occurrences: 57 Examples: * ਚੌਕਸੀ: [t͡ʃ ɔ k s i] * ਕੌੜ: [k ɔ ɽ] * ਮੌਕੇ: [m ɔ k e] * ਲੌਢਾ: [l ɔ ʈ ɑ] |
|||
Open |
Occurrences: 1,514 Examples: * ਰਜਾ: [ɾ ə d͡ʒ ɑ] * ਸੰਦੜਾ: [s ə̃ d̪ ə ɽ ɑ] * ਚਾਨਣ: [t͡ʃ ɑ n ə ɳ] * ਸਾਡਾ: [s ɑ ɖ ɑ] |
Nasal Vowels#
Front |
Near-Front |
Central |
Near-Back |
Back |
|
---|---|---|---|---|---|
Close |
Occurrences: 30 Examples: * ਨਜ਼ਰੀਂ: [n ə z ɾ ĩ] * ਜੰਮੀਂ: [d͡ʒ ə̃ m ĩ] * ਹੋਠੀਂ: [ɦ o ʈʰ ĩ] * ਕਰਨੀਂ: [k ə ɾ n ĩ] |
Occurrences: 30 Examples: * ਇਹਨੂੰ: [ɪ ɦ n ũ] * ਸਾਨੂੰ: [s ɑ n ũ] * ਮੈਨੂੰ: [m ɛ n ũ] * ਉਹਨੂੰ: [ʊ ɦ n ũ] |
|||
Occurrences: 66 Examples: * ਇੰਨਾਂ: [ɪ̃ n ɑ̃] * ਪਿੰਡ: [p ɪ̃ ɖ] * ਹਿੰਦੂ: [ɦ ɪ̃ d̪ u] * ਹਿੰਦੀ: [ɦ ɪ̃ d̪ i] |
Occurrences: 49 Examples: * ਆਉਂਦੀ: [ɑ ʊ̃ d̪ i] * ਤੂਈਉਂ: [t̪ u i ʊ̃] * ਹੁੰਦਾ: [ɦ ʊ̃ d̪ ɑ] * ਹੁੰਦੈ: [ɦ ʊ̃ d̪ ɛ] |
||||
Close-Mid |
Occurrences: 19 Examples: * ਤੋੇਂ: [t̪ o ẽ] * ਐਵੇਂ: [ɛ ʋ ẽ] * ਸਮੇਂ: [s ə m ẽ] * ਨੀਵੇਂ: [n i ʋ ẽ] |
Occurrences: 40 Examples: * ਮੈਥੋਂ: [m ɛ t̪ʰ õ] * ਵੱਲੋਂ: [ʋ ə lː õ] * ਦੋਂਨੇ: [d̪ õ n e] * ਕਦੋਂ: [k ə d̪ õ] |
|||
Occurrences: 193 Examples: * ਅੰਕੜੇ: [ə̃ k ə ɽ e] * ਬਰੰਗੇ: [b ə ɾ ə̃ ɡ e] * ਸੰਦੜਾ: [s ə̃ d̪ ə ɽ ɑ] * ਸੰਦੇਸ਼: [s ə̃ d̪ e ʃ] |
|||||
Open-Mid |
Occurrences: 30 Examples: * ਪੈਂਦੀ: [p ɛ̃ d̪ i] * ਹੈਂ: [ɦ ɛ̃] * ਬੈਂਕ: [b ɛ̃ k] * ਸ਼ੈਂਪੂ: [ʃ ɛ̃ p u] |
Occurrences: 5 Examples: * ਕੌਂਸਲ: [k ɔ̃ s ə l] |
|||
Open |
Occurrences: 413 Examples: * ਗਾਂਧੀ: [ɡ ɑ̃ t̪ i] * ਯਤਨਾਂ: [j ə t̪ n ɑ̃] * ਮਾਂ: [m ɑ̃] * ਉਨਾਂ: [ʊ n ɑ̃] |