Ctrl+K
Ctrl+K

Hungarian CV dictionary v2.0.0#

  • Maintainer: Vox Communis

  • Language: Hungarian

  • Dialect: N/A

  • Phone set: XPF

  • Number of words: 27,181

  • Phones: aː b bː c cː d dː eː f fː h hː i iː j jː k kː l lː m mː n nː o oː p pː r rː s sː t ts tsː tʃ tʃː tː u uː v vː y yː z zː ø øː ɑ ɛ ɟ ɟː ɡ ɡː ɲ ɲː ʃ ʃː ʒ

  • License: CC-0

  • Compatible MFA version: v2.0.0

  • Citation:

@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 hungarian_cv

Or download from the release page.

Intended use#

This dictionary is intended for forced alignment of Hungarian transcripts.

This dictionary uses the XPF phone set for Hungarian, and was used in training the Hungarian 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

Glottal

Nasal
Occurrences:
6,681
Examples:
* mára:
[m aː r ɑ]
* mamba:
[m ɑ m b ɑ]
* venom:
[v ɛ n o m]
* üzemi:
[y z ɛ m i]
Occurrences:
97
Examples:
* somme:
[ʃ o mː ɛ]
* bumm:
[b u mː]
* tommy:
[t o mː i]
* jimmy:
[j i mː i]
Occurrences:
11,029
Examples:
* janka:
[j ɑ n k ɑ]
* igent:
[i ɡ ɛ n t]
* abban:
[ɑ bː ɑ n]
* kun:
[k u n]
Occurrences:
243
Examples:
* inni:
[i nː i]
* mannt:
[m ɑ nː t]
* hinni:
[h i nː i]
* innen:
[i nː ɛ n]
Occurrences:
1,645
Examples:
* anyám:
[ɑ ɲ aː m]
* lánya:
[l aː ɲ ɑ]
* idény:
[i d eː ɲ]
* enyém:
[ɛ ɲ eː m]
Occurrences:
95
Examples:
* penny:
[p ɛ ɲː]
* ennyi:
[ɛ ɲː i]
* denny:
[d ɛ ɲː]
* ronny:
[r o ɲː]

Stop
Occurrences:
2,885
Examples:
* napig:
[n ɑ p i ɡ]
* lépek:
[l eː p ɛ k]
* pilis:
[p i l i ʃ]
* kupa:
[k u p ɑ]
Occurrences:
74
Examples:
* hopp:
[h o pː]
* csepp:
[tʃ ɛ pː]
* épp:
[eː pː]
* éppen:
[eː pː ɛ n]
Occurrences:
4,526
Examples:
* mamba:
[m ɑ m b ɑ]
* blore:
[b l o r ɛ]
* bűnös:
[b yː n ø ʃ]
* betűk:
[b ɛ t yː k]
Occurrences:
366
Examples:
* abban:
[ɑ bː ɑ n]
* üdébb:
[y d eː bː]
* ebbe:
[ɛ bː ɛ]
* ebből:
[ɛ bː øː l]
Occurrences:
15,997
Examples:
* tudós:
[t u d oː ʃ]
* hit:
[h i t]
* igent:
[i ɡ ɛ n t]
* várat:
[v aː r ɑ t]
Occurrences:
1,918
Examples:
* nőtt:
[n øː tː]
* lett:
[l ɛ tː]
* kettő:
[k ɛ tː øː]
* nőtte:
[n øː tː ɛ]
Occurrences:
5,125
Examples:
* tudós:
[t u d oː ʃ]
* jeled:
[j ɛ l ɛ d]
* tudna:
[t u d n ɑ]
* kendó:
[k ɛ n d oː]
Occurrences:
62
Examples:
* eddig:
[ɛ dː i ɡ]
* vidd:
[v i dː]
* addig:
[ɑ dː i ɡ]
* toldd:
[t o l dː]
Occurrences:
115
Examples:
* atyám:
[ɑ c aː m]
* tyler:
[c l ɛ r]
* monty:
[m o n c]
* atyja:
[ɑ c j ɑ]
Occurrences:
18
Examples:
* fütty:
[f y cː]
Occurrences:
1,318
Examples:
* gyári:
[ɟ aː r i]
* ágya:
[aː ɟ ɑ]
* ágyás:
[aː ɟ aː ʃ]
* lágy:
[l aː ɟ]
Occurrences:
28
Examples:
Occurrences:
12,686
Examples:
* janka:
[j ɑ n k ɑ]
* hízik:
[h iː z i k]
* kun:
[k u n]
* lanka:
[l ɑ n k ɑ]
Occurrences:
262
Examples:
* sakk:
[ʃ ɑ kː]
* trükk:
[t r y kː]
* cikke:
[ts i kː ɛ]
* akkor:
[ɑ kː o r]
Occurrences:
5,401
Examples:
* igent:
[i ɡ ɛ n t]
* napig:
[n ɑ p i ɡ]
* eddig:
[ɛ dː i ɡ]
* végre:
[v eː ɡ r ɛ]
Occurrences:
123
Examples:
* jéggé:
[j eː ɡː eː]
* zengg:
[z ɛ n ɡː]
* függő:
[f y ɡː øː]
* függ:
[f y ɡː]

Affricate
Occurrences:
1,178
Examples:
* cella:
[ts ɛ lː ɑ]
* címen:
[ts iː m ɛ n]
* cél:
[ts eː l]
* duc:
[d u ts]
Occurrences:
24
Examples:
* secco:
[ʃ ɛ tsː o]
* vicc:
[v i tsː]
* gucci:
[ɡ u tsː i]
Occurrences:
1,241
Examples:
* puncs:
[p u n tʃ]
* cseh:
[tʃ ɛ h]
* bocs:
[b o tʃ]
* kocsi:
[k o tʃ i]
Occurrences:
12
Examples:
* meccs:
[m ɛ tʃː]
* öccse:
[ø tʃː ɛ]

Sibilant
Occurrences:
4,193
Examples:
* eszi:
[ɛ s i]
* tudsz:
[t u d s]
* szőni:
[s øː n i]
* hívsz:
[h iː v s]
Occurrences:
346
Examples:
* rossz:
[r o sː]
* össze:
[ø sː ɛ]
* jössz:
[j ø sː]
* mássz:
[m aː sː]
Occurrences:
4,063
Examples:
* hízik:
[h iː z i k]
* üzemi:
[y z ɛ m i]
* nehéz:
[n ɛ h eː z]
* azon:
[ɑ z o n]
Occurrences:
124
Examples:
* hozza:
[h o zː ɑ]
* bízza:
[b iː zː ɑ]
* pizza:
[p i zː ɑ]
* izzad:
[i zː ɑ d]
Occurrences:
7,165
Examples:
* tudós:
[t u d oː ʃ]
* erős:
[ɛ r øː ʃ]
* festő:
[f ɛ ʃ t øː]
* bűnös:
[b yː n ø ʃ]
Occurrences:
344
Examples:
* messi:
[m ɛ ʃː i]
* friss:
[f r i ʃː]
* süss:
[ʃ y ʃː]
* mossa:
[m o ʃː ɑ]
Occurrences:
253
Examples:
* zsebe:
[ʒ ɛ b ɛ]
* zsolt:
[ʒ o l t]
* zsák:
[ʒ aː k]
* rózsa:
[r oː ʒ ɑ]

Fricative
Occurrences:
2,635
Examples:
* festő:
[f ɛ ʃ t øː]
* fárad:
[f aː r ɑ d]
* fogta:
[f o ɡ t ɑ]
* fejet:
[f ɛ j ɛ t]
Occurrences:
17
Examples:
* off:
[o fː]
* bluff:
[b l u fː]
Occurrences:
4,415
Examples:
* várat:
[v aː r ɑ t]
* venom:
[v ɛ n o m]
* lévén:
[l eː v eː n]
* jóval:
[j oː v ɑ l]
Occurrences:
10
Examples:
* évvel:
[eː vː ɛ l]
* evvel:
[ɛ vː ɛ l]
Occurrences:
3,530
Examples:
* hit:
[h i t]
* hopp:
[h o pː]
* hízik:
[h iː z i k]
* hozza:
[h o zː ɑ]
Occurrences:
5
Examples:
* ehhez:
[ɛ hː ɛ z]
* ahhoz:
[ɑ hː o z]

Approximant
Occurrences:
3,847
Examples:
* janka:
[j ɑ n k ɑ]
* állj:
[aː lː j]
* jeled:
[j ɛ l ɛ d]
* ily:
[i j]
Occurrences:
71
Examples:
* ujjai:
[u jː ɑ i]
* éjjel:
[eː jː ɛ l]
* újjá:
[uː jː aː]
* ujjad:
[u jː ɑ d]

Trill
Occurrences:
10,933
Examples:
* mára:
[m aː r ɑ]
* várat:
[v aː r ɑ t]
* áron:
[aː r o n]
* blore:
[b l o r ɛ]
Occurrences:
180
Examples:
* orrot:
[o rː o t]
* várra:
[v aː rː ɑ]
* varrt:
[v ɑ rː t]
* sárrá:
[ʃ aː rː aː]

Lateral
Occurrences:
12,694
Examples:
* blore:
[b l o r ɛ]
* jeled:
[j ɛ l ɛ d]
* túlra:
[t uː l r ɑ]
* lanka:
[l ɑ n k ɑ]
Occurrences:
924
Examples:
* állj:
[aː lː j]
* cella:
[ts ɛ lː ɑ]
* illik:
[i lː i k]
* széll:
[s eː lː]

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:
9,524
Examples:
* hit:
[h i t]
* igent:
[i ɡ ɛ n t]
* hízik:
[h iː z i k]
* gyári:
[ɟ aː r i]
Occurrences:
1,714
Examples:
* hízik:
[h iː z i k]
* kiírt:
[k i iː r t]
* címen:
[ts iː m ɛ n]
* íve:
[iː v ɛ]
Occurrences:
1,426
Examples:
* üzemi:
[y z ɛ m i]
* ültek:
[y l t ɛ k]
* dühbe:
[d y h b ɛ]
* füves:
[f y v ɛ ʃ]
Occurrences:
237
Examples:
* bűnös:
[b yː n ø ʃ]
* betűk:
[b ɛ t yː k]
* derű:
[d ɛ r yː]
* hűtöd:
[h yː t ø d]
Occurrences:
3,201
Examples:
* tudós:
[t u d oː ʃ]
* kun:
[k u n]
* tudna:
[t u d n ɑ]
* liu:
[l i u]
Occurrences:
806
Examples:
* túlra:
[t uː l r ɑ]
* lúd:
[l uː d]
* rangú:
[r ɑ n ɡ uː]
* húrt:
[h uː r t]

Close-Mid
Occurrences:
7,518
Examples:
* ért:
[eː r t]
* lévén:
[l eː v eː n]
* végre:
[v eː ɡ r ɛ]
* téged:
[t eː ɡ ɛ d]
Occurrences:
2,659
Examples:
* költő:
[k ø l t øː]
* bűnös:
[b yː n ø ʃ]
* körét:
[k ø r eː t]
* köt:
[k ø t]
Occurrences:
2,086
Examples:
* erős:
[ɛ r øː ʃ]
* költő:
[k ø l t øː]
* festő:
[f ɛ ʃ t øː]
* nőtt:
[n øː tː]
Occurrences:
10,398
Examples:
* hopp:
[h o pː]
* áron:
[aː r o n]
* venom:
[v ɛ n o m]
* hozza:
[h o zː ɑ]
Occurrences:
2,655
Examples:
* tudós:
[t u d oː ʃ]
* kendó:
[k ɛ n d oː]
* ólmos:
[oː l m o ʃ]
* jóval:
[j oː v ɑ l]

Open-Mid
Occurrences:
23,023
Examples:
* igent:
[i ɡ ɛ n t]
* venom:
[v ɛ n o m]
* blore:
[b l o r ɛ]
* jeled:
[j ɛ l ɛ d]

Open
Occurrences:
9,857
Examples:
* mára:
[m aː r ɑ]
* várat:
[v aː r ɑ t]
* áron:
[aː r o n]
* állj:
[aː lː j]
Occurrences:
17,565
Examples:
* janka:
[j ɑ n k ɑ]
* abban:
[ɑ bː ɑ n]
* mára:
[m aː r ɑ]
* várat:
[v aː r ɑ t]
On this page
Show Source