Model Card for korean_mfa
This MFA model is for aligning Korean speech.
Model Details
Model Description
- Developed by: Michael McAuliffe
- Funded by: N/A
- Model type: Montreal Forced Aligner model
- Language(s) (NLP): Korean
- License: cc-by-4.0
Uses
Direct Use
This model is intended to be used for forced alignment of Korean speech. Please see https://montreal-forced-aligner.readthedocs.io/en/latest/user_guide/troubleshooting.html for details on common fixes.
Out-of-Scope Use
This model cannot provide accurate assessments of goodness of pronunciations or provide transcripts as it is trained to be accepting of variation in pronunciation to provide a reasonable alignment for Korean speech.
Bias, Risks, and Limitations
This model will perform best on the variety of speech that it was trained on. The speakers in the training data are all adult speakers, so child speech alignment may not be accurate.
Recommendations
When using this model on a variety that it was not trained on, better results can be attained by adapting the model to the data to be aligned first. See https://montreal-forced-aligner.readthedocs.io/en/latest/user_guide/workflows/adapt_acoustic_model.html and https://github.com/mmcauliffe/mfa-adaptation for example usage and scripts.
How to Get Started with the Model
Use the code below to get started with the model.
To get started, follow the instructions for installing MFA. To align files using this model, use the mfa align command.
Dictionary Details
Details for korean_mfa dictionary and G2P model
- Source: wikipron
- Orthography: Hangul
- Phone set: MFA
- Words: 79,188
- Phones: 95
- Graphemes: 2,250
IPA chart
Consonants
| Manner | Labial | Alveolar | Retroflex | Palatal | Velar | Glottal |
|---|---|---|---|---|---|---|
| Nasal | m mː | n nː | ɲ | ŋ | ||
| Palatalized | mʲ mʲː | |||||
| Stop | p b | t d | c ɟ | k ɡ | ||
| Tense | p͈ | t͈ t͈ː | c͈ | k͈ k͈ː | ||
| Aspirated | pʰ pʰː | tʰ tʰː | cʰ cʰː | kʰ kʰː | ||
| Unreleased | p̚ | t̚ | k̚ | |||
| Labialized | pʷ bʷ | tʷ tʷː dʷ | kʷ kʷː ɡʷ | |||
| Palatalized | pʲ pʲː bʲ | tʲ dʲ | ||||
| Affricate | tɕ tɕː dʑ | |||||
| Tense | tɕ͈ tɕ͈ː | |||||
| Aspirated | tɕʰ tɕʰː | |||||
| Labialized | tɕʷ tɕʷː dʑʷ | |||||
| Sibilant | s sː | |||||
| Tense | s͈ | ɕ͈ | ||||
| Aspirated | sʰ sʰː | ɕʰ | ||||
| Labialized | sʷ | |||||
| Fricative | ç ʝ | h ɦ | ||||
| Labialized | ɸʷ | |||||
| Approximant | w | j ɥ | ɰ | |||
| Tap | ɾ | |||||
| Labialized | ɾʷ | |||||
| Palatalized | ɾʲ | |||||
| Lateral | ʎ ʎː | |||||
| Lateral Tap | ɭ ɭː |
Vowels
| Front | Near-Front | Central | Near-Back | Back | |
|---|---|---|---|---|---|
| Close | i iː | ɨ ɨː | u uː | ||
| Close-Mid | e eː | o oː | |||
| Open-Mid | ɛ ɛː | ʌ ʌː | |||
| ɐ | |||||
| Open |
Training Details
Training Data
Common Voice Korean
- Source: https://voice.mozilla.org/en/datasets
- License: CC-0
- Dialects: N/A
- Number of hours: 1.41
- Number of utterances: 916
- Number of speakers: 46
- Female speakers: 7
- Male speakers: 15
- Unknown speakers: 24
GlobalPhone Korean
- Source: https://catalogue.elra.info/en-us/repository/browse/ELRA-S0200/
- License: ELRA
- Dialects: N/A
- Number of hours: 20.88
- Number of utterances: 8,007
- Number of speakers: 99
- Female speakers: 50
- Male speakers: 49
- Unknown speakers: 0
Deeply Korean read speech corpus public sample
- Source: https://www.openslr.org/97/
- License: CC BY-NC-ND 4.0
- Dialects: N/A
- Number of hours: 2.93
- Number of utterances: 1,697
- Number of speakers: 2
- Female speakers: 2
- Male speakers: 0
- Unknown speakers: 0
ASR-KCSC A Korean Conversational Speech Corpus
- Source: https://magichub.com/datasets/korean-conversational-speech-corpus/
- License: CC BY-NC-ND 4.0
- Dialects: N/A
- Number of hours: 2.38
- Number of utterances: 4,404
- Number of speakers: 14
- Female speakers: 4
- Male speakers: 10
- Unknown speakers: 0
ASR-SKDuSC A Scripted Korean Daily-use Speech Corpus
- Source: https://magichub.com/datasets/korean-scripted-speech-corpus-daily-use-sentence/
- License: CC BY-NC-ND 4.0
- Dialects: N/A
- Number of hours: 3.90
- Number of utterances: 5,240
- Number of speakers: 10
- Female speakers: 5
- Male speakers: 5
- Unknown speakers: 0
Korean Single Speaker Speech Dataset
- Source: https://www.kaggle.com/datasets/bryanpark/korean-single-speaker-speech-dataset
- License: CC BY-NC-SA 4.0
- Dialects: N/A
- Number of hours: 12.86
- Number of utterances: 12,854
- Number of speakers: 40
- Female speakers: 1
- Male speakers: 0
- Unknown speakers: 0
Pansori TEDxKR
- Source: http://www.openslr.org/58/
- License: CC BY-NC-ND 4.0
- Dialects: N/A
- Number of hours: 2.69
- Number of utterances: 2,989
- Number of speakers: 41
- Female speakers: 9
- Male speakers: 32
- Unknown speakers: 0
Zeroth Korean
- Source: https://openslr.org/40/
- License: CC BY 4.0
- Dialects: N/A
- Number of hours: 52.87
- Number of utterances: 22,720
- Number of speakers: 115
- Female speakers: 70
- Male speakers: 45
- Unknown speakers: 0
Training Procedure
Preprocessing
Preprocessing include fixes and orthographic standardization to various corpora.
Training Hyperparameters
- Training regime: Training configuration
Evaluation
Testing Data, Factors & Metrics
Testing Data
N/A
Factors
N/A
Metrics
N/A
Results
N/A
Summary
Technical Specifications
Model Architecture and Objective
HMM-GMM model
Software
This model was trained via the Montreal Forced Aligner.
Citation
BibTeX:
@techreport{mfa_korean_mfa_acoustic_2026,
author={McAuliffe, Michael and Sonderegger, Morgan},
title={Korean MFA acoustic model v3.3.0},
address={\url{https://huggingface.co/MontrealCorpusTools/korean_mfa}},
year={2026},
month={Jun},
}
APA:
McAuliffe, M. & Sonderegger, M. (2026). Korean MFA acoustic model v3.3.0. Available at https://huggingface.co/MontrealCorpusTools/korean_mfa.
Contact
For questions and issues, please file an issue either for this model at https://huggingface.co/MontrealCorpusTools/korean_mfa/discussions or for larger MFA issues at https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner/issues.