Sorbian (Upper) 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}
}
Acoustic models |
Installation#
Install from the MFA command line:
mfa model download dictionary sorbian_upper_cv
Or download from the release page.
Intended use#
This dictionary is intended for forced alignment of Sorbian transcripts.
This dictionary uses the XPF phone set for Sorbian, and was used in training the Sorbian XPF 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 |
Alveolar |
Alveopalatal |
Palatal |
Velar |
Uvular |
Glottal |
---|---|---|---|---|---|---|---|---|
Nasal |
Occurrences: 1,312 Examples: * mamoj: [m a m o j] * romow: [ʀ o m o w] * štomy: [ʃ t o m ɨ] * zemrě: [z e m ʀ ɪ] Occurrences: 104 Examples: * temje: [t e mʲ e] * domje: [d o mʲ e] * rumje: [ʀ u mʲ e] * jamje: [j a mʲ e] |
Occurrences: 2,205 Examples: * nic: [n i ts] * knize: [k n i z e] * nóc: [n ʊ ts] * rhön: [ʀ h o n] Occurrences: 725 Examples: * njeho: [nʲ e h o] * nju: [nʲ u] * njej: [nʲ e j] * dóńdu: [d ʊ nʲ d u] |
||||||
Stop |
Occurrences: 1,142 Examples: * pyta: [p ɨ t a] * hłupa: [h w u p a] * prosy: [p ʀ o s ɨ] * pora: [p o ʀ a] Occurrences: 671 Examples: * zbožo: [z b o ʒ o] * bliža: [b l i ʒ a] * była: [b ɨ w a] * blogu: [b l o ɡ u] |
Occurrences: 1,644 Examples: * haty: [h a t ɨ] * pyta: [p ɨ t a] * tesće: [t e s tʃ e] * tale: [t a l e] Occurrences: 1,065 Examples: * dróhi: [d ʀ ʊ h i] * widom: [w i d o m] * dróze: [d ʀ ʊ z e] * domje: [d o mʲ e] |
Occurrences: 1,662 Examples: * knize: [k n i z e] * wulki: [w u l k i] * łaka: [w a k a] * šklě: [ʃ k l ɪ] Occurrences: 149 Examples: * blogu: [b l o ɡ u] * gipsa: [ɡ i p s a] * liga: [l i ɡ a] * organ: [o ʀ ɡ a n] |
|||||
Affricate |
Occurrences: 526 Examples: * nic: [n i ts] * nóc: [n ʊ ts] * tysac: [t ɨ s a ts] * cyłym: [ts ɨ w ɨ m] |
Occurrences: 1,037 Examples: * wočow: [w o tʃ o w] * tesće: [t e s tʃ e] * sćěhi: [s tʃ ɪ h i] * witać: [w i t a tʃ] Occurrences: 371 Examples: * dźěle: [dʒ ɪ l e] * dźěše: [dʒ ɪ ʃ e] * radźe: [ʀ a dʒ e] * dźěło: [dʒ ɪ w o] |
||||||
Sibilant |
Occurrences: 1,987 Examples: * tesće: [t e s tʃ e] * sćěhi: [s tʃ ɪ h i] * stat: [s t a t] * tysac: [t ɨ s a ts] Occurrences: 844 Examples: * knize: [k n i z e] * zbožo: [z b o ʒ o] * zemrě: [z e m ʀ ɪ] * wza: [w z a] |
Occurrences: 816 Examples: * štomy: [ʃ t o m ɨ] * dźěše: [dʒ ɪ ʃ e] * šklě: [ʃ k l ɪ] * lěpša: [l ɪ p ʃ a] Occurrences: 335 Examples: * zbožo: [z b o ʒ o] * móžu: [m ʊ ʒ u] * žurli: [ʒ u ʀ l i] * wěžu: [w ɪ ʒ u] |
||||||
Fricative |
Occurrences: 130 Examples: * štefi: [ʃ t e f i] * fraku: [f ʀ a k u] * wolf: [w o l f] * farar: [f a ʀ a ʀ] Occurrences: 3 Examples: |
Occurrences: 549 Examples: * haty: [h a t ɨ] * dróhi: [d ʀ ʊ h i] * sćěhi: [s tʃ ɪ h i] * rhön: [ʀ h o n] |
||||||
Approximant |
Occurrences: 2,786 Examples: * wočow: [w o tʃ o w] * romow: [ʀ o m o w] * widom: [w i d o m] * wza: [w z a] Occurrences: 190 Examples: * wjesć: [wʲ e s tʃ] * wjele: [wʲ e l e] * wjelk: [wʲ e l k] * wjedu: [wʲ e d u] |
Occurrences: 1,179 Examples: * mamoj: [m a m o j] * maja: [m a j a] * moje: [m o j e] * jedne: [j e d n e] |
||||||
Trill |
Occurrences: 1,667 Examples: * dróhi: [d ʀ ʊ h i] * romow: [ʀ o m o w] * zemrě: [z e m ʀ ɪ] * žurli: [ʒ u ʀ l i] Occurrences: 247 Examples: * rjane: [ʀʲ a n e] * rjad: [ʀʲ a d] * měrje: [m ɪ ʀʲ e] * drje: [d ʀʲ e] |
|||||||
Lateral |
Occurrences: 977 Examples: * tale: [t a l e] * dźěle: [dʒ ɪ l e] * žurli: [ʒ u ʀ l i] * lipju: [l i pʲ u] |
Vowels#
Vowel symbols to the left of are unrounded and those to the right are rounded.
Front |
Near-Front |
Central |
Near-Back |
Back |
|
---|---|---|---|---|---|
Close |
Occurrences: 2,437 Examples: * nic: [n i ts] * dróhi: [d ʀ ʊ h i] * knize: [k n i z e] * sćěhi: [s tʃ ɪ h i] |
Occurrences: 968 Examples: * haty: [h a t ɨ] * pyta: [p ɨ t a] * štomy: [ʃ t o m ɨ] * tysac: [t ɨ s a ts] |
Occurrences: 1,646 Examples: * móžu: [m ʊ ʒ u] * žurli: [ʒ u ʀ l i] * lipju: [l i pʲ u] * wěžu: [w ɪ ʒ u] |
||
Occurrences: 694 Examples: * sćěhi: [s tʃ ɪ h i] * zemrě: [z e m ʀ ɪ] * dźěle: [dʒ ɪ l e] * dźěše: [dʒ ɪ ʃ e] |
Occurrences: 285 Examples: * dróhi: [d ʀ ʊ h i] * nóc: [n ʊ ts] * móžu: [m ʊ ʒ u] * dróze: [d ʀ ʊ z e] |
||||
Close-Mid |
Occurrences: 3,569 Examples: * tesće: [t e s tʃ e] * knize: [k n i z e] * tale: [t a l e] * temje: [t e mʲ e] |
Occurrences: 3,405 Examples: * wočow: [w o tʃ o w] * mamoj: [m a m o j] * zbožo: [z b o ʒ o] * romow: [ʀ o m o w] |
|||
Open-Mid |
|||||
Open |
Occurrences: 4,075 Examples: * haty: [h a t ɨ] * pyta: [p ɨ t a] * mamoj: [m a m o j] * tale: [t a l e] |