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 Turkish 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 turkish_mfa dictionary and G2P model

Source: wikipron
Orthography: Latin
Phone set: MFA
Words: 94,632

Phones: 70
Graphemes: 52

IPA chart

Consonants

Manner	Labial	Labiodental	Dental	Alveolar	Alveopalatal	Palatal	Velar	Glottal
Nasal	m mː		n̪ n̪ː			ɲ	ŋ
Stop	p pː b bː		t̪ t̪ː d̪ d̪ː			c cː ɟ ɟː	k kː ɡ
Affricate					tʃ tʃː dʒ dʒː
Sibilant			s̪ s̪ː z̪ z̪ː		ʃ ʃː ʒ
Fricative		f fː v vː				ç çː		h hː
Approximant						j jː
Tap				ɾ ɾː
Lateral				ɫ ɫː		ʎ ʎː

Vowels

	Front	Near-Front	Central	Near-Back	Back
Close	i iː y yː		ɨ		ɯ ɯː u uː
		ɪ ʏ		ʊ
Close-Mid	e eː ø øː				o oː

Open-Mid	ɛ œ

Open			a aː

Training Details

Training Data

Common Voice Turkish

Source: https://voice.mozilla.org/en/datasets
License: CC-0
Dialects: N/A
Number of hours: 111.06
Number of utterances: 110,431
Number of speakers: 1,453
- Female speakers: 60
- Male speakers: 377
- Unknown speakers: 1,016

GlobalPhone Turkish

Source: https://catalogue.elra.info/en-us/repository/browse/ELRA-S0206/
License: ELRA
Dialects: N/A
Number of hours: 17.12
Number of utterances: 6,949
Number of speakers: 100
- Female speakers: 72
- Male speakers: 28
- 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_turkish_mfa_acoustic_2026,
	author={McAuliffe, Michael and Sonderegger, Morgan},
	title={Turkish MFA acoustic model v3.3.0},
	address={\url{https://huggingface.co/MontrealCorpusTools/turkish_mfa}},
	year={2026},
	month={Jun},
}

APA:

McAuliffe, M. & Sonderegger, M. (2026). Turkish MFA acoustic model v3.3.0. Available at https://huggingface.co/MontrealCorpusTools/turkish_mfa.

Contact

For questions and issues, please file an issue either for this model at https://huggingface.co/MontrealCorpusTools/turkish_mfa/discussions or for larger MFA issues at https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner/issues.