Hugging Face's logo

MontrealCorpusTools
/
spanish_mfa

Other
Spanish
montreal-forced-aligner
forced-alignment
Model card Files
xet
 Community

Model Card for spanish_mfa

This MFA model is for aligning Spanish speech.

Model Details

Model Description

  • Developed by: Michael McAuliffe
  • Funded by: N/A
  • Model type: Montreal Forced Aligner model
  • Language(s) (NLP): Spanish
  • License: cc-by-4.0

Uses

Direct Use

This model is intended to be used for forced alignment of Spanish 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 Spanish 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 spanish_latin_america_mfa dictionary and G2P model

  • Source: wikipron
  • Orthography: Latin
  • Phone set: MFA
  • Words: 320,402
  • Phones: 40
  • Graphemes: 113
IPA chart
Consonants
Manner Labial Labiodental Dental Alveolar Alveopalatal Palatal Velar Glottal
Nasal m ɱ n ɲ ŋ
Stop p b t̪ d̪ c ɟ k ɡ
Affricate tʃ ɟʝ
Sibilant s z ʃ
Fricative f v ð ç ʝ h
Approximant w j
Tap ɾ
Trill r
Lateral l ʎ
Vowels

Oral vowels

Front Near-Front Central Near-Back Back
Close i u
Close-Mid e o
Open-Mid
Open a

Nasal vowels

Front Near-Front Central Near-Back Back
Close ĩ ũ
Close-Mid ẽ õ
Open-Mid
Open ã

Details for spanish_spain_mfa dictionary and G2P model

  • Source: wikipron
  • Orthography: Latin
  • Phone set: MFA
  • Words: 437,782
  • Phones: 41
  • Graphemes: 82
IPA chart
Consonants
Manner Labial Labiodental Dental Alveolar Alveopalatal Palatal Velar Glottal
Nasal m ɱ n ɲ ŋ
Stop p b t̪ d̪ c ɟ k ɡ
Affricate tʃ ɟʝ
Sibilant s z ʃ
Fricative f v θ ð ç ʝ h
Approximant w j
Tap ɾ
Trill r
Lateral l ʎ
Vowels

Oral vowels

Front Near-Front Central Near-Back Back
Close i u
Close-Mid e o
Open-Mid
Open a

Nasal vowels

Front Near-Front Central Near-Back Back
Close ĩ ũ
Close-Mid ẽ õ
Open-Mid
Open ã

Training Details

Training Data

Common Voice Spanish

  • Source: https://voice.mozilla.org/en/datasets
  • License: CC-0
  • Dialects: spain, latin america
  • Number of hours: 670.81
  • Number of utterances: 480,819
  • Number of speakers: 22,028
    • Female speakers: 1,198
    • Male speakers: 3,431
    • Unknown speakers: 17,399

GlobalPhone Spanish (Latin American)

Google i18n Chile

  • Source: https://openslr.org/71/
  • License: CC BY-SA 4.0
  • Dialects: latin america
  • Number of hours: 7.15
  • Number of utterances: 4,374
  • Number of speakers: 31
    • Female speakers: 13
    • Male speakers: 18
    • Unknown speakers: 0

Google i18n Columbia

  • Source: https://openslr.org/71/
  • License: CC BY-SA 4.0
  • Dialects: latin america
  • Number of hours: 7.58
  • Number of utterances: 4,903
  • Number of speakers: 33
    • Female speakers: 16
    • Male speakers: 17
    • Unknown speakers: 0

Google i18n Peru

  • Source: https://openslr.org/71/
  • License: CC BY-SA 4.0
  • Dialects: latin america
  • Number of hours: 9.22
  • Number of utterances: 5,447
  • Number of speakers: 38
    • Female speakers: 18
    • Male speakers: 20
    • Unknown speakers: 0

Google i18n Puerto Rico

  • Source: https://openslr.org/71/
  • License: CC BY-SA 4.0
  • Dialects: latin america
  • Number of hours: 1.00
  • Number of utterances: 617
  • Number of speakers: 5
    • Female speakers: 5
    • Male speakers: 0
    • Unknown speakers: 0

Google i18n Venezuela

  • Source: https://openslr.org/71/
  • License: CC BY-SA 4.0
  • Dialects: latin america
  • Number of hours: 4.81
  • Number of utterances: 3,357
  • Number of speakers: 23
    • Female speakers: 11
    • Male speakers: 12
    • Unknown speakers: 0

Multilingual LibriSpeech Spanish

  • Source: https://openslr.org/94/
  • License: CC BY 4.0
  • Dialects: spain
  • Number of hours: 938.30
  • Number of utterances: 225,494
  • Number of speakers: 126
    • Female speakers: 70
    • Male speakers: 56
    • Unknown speakers: 0

Multilingual TEDx Spanish

  • Source: https://www.openslr.org/100/
  • License: CC BY-NC-ND 4.0
  • Dialects: spain, latin america
  • Number of hours: 176.18
  • Number of utterances: 72,504
  • Number of speakers: 1,068
    • Female speakers: 0
    • Male speakers: 0
    • Unknown speakers: 1,068

M-AILABS Spanish

  • Source: https://openslr.org/94/
  • License: M-AILABS License
  • Dialects: spain, latin america
  • Number of hours: 108.57
  • Number of utterances: 59,296
  • Number of speakers: 21
    • Female speakers: 11
    • Male speakers: 10
    • Unknown speakers: 0

Training Procedure

Preprocessing

Preprocessing include fixes and orthographic standardization to various corpora.

Training Hyperparameters

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_spanish_mfa_acoustic_2026,
    author={McAuliffe, Michael and Sonderegger, Morgan},
    title={Spanish MFA acoustic model v3.3.0},
    address={\url{https://huggingface.co/MontrealCorpusTools/spanish_mfa}},
    year={2026},
    month={Jun},
}

APA:

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

Contact

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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Other
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support