README.md

---
language:
- pt
pipeline_tag: other
library_name: montreal-forced-aligner
tags:
- montreal-forced-aligner
- forced-alignment
license: cc-by-4.0
---
# Model Card for portuguese_mfa

<!-- Provide a quick summary of what the model is/does. -->

This MFA model is for aligning Portuguese across Brazil and Portugal dialects.

- [Model details](#model-details)
- [Uses](#uses)
- [Performance Factors](#how-to-get-started-with-the-model)
- [Dictionary Details](#dictionary-details)
- [Training Details](#training-details)
- [Evaluation](#evaluation)
- [Contact](#contact)

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



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

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model is intended to be used for forced alignment of Portuguese varieties that it was trained on (Portugal and Brazil).  Please see https://montreal-forced-aligner.readthedocs.io/en/latest/user_guide/troubleshooting.html for details on common fixes.

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

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 Portuguese speech.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

This model will perform best on the variety of speech that it was trained on, with a bias towards Brazilian Portuguese.  The speakers in the training data are all adult speakers, so child speech alignment may not be accurate.

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

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](https://montreal-forced-aligner.readthedocs.io/en/latest/getting_started.html). To align files using this model, use the [mfa align](https://montreal-forced-aligner.readthedocs.io/en/latest/user_guide/workflows/alignment.html) command.

## Dictionary Details

#### Details for portuguese_portugal_mfa dictionary and G2P model

- **Source:** wikipron
- **Orthography:** Latin
- **Phone set:** MFA
- **Words:** 117,496
* **Phones:** 42
* **Graphemes:** 82

##### IPA chart

###### Consonants

| Manner | Labial | Labiodental | Dental | Alveolar | Alveopalatal | Palatal | Velar | Uvular |
| :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: |
| **Nasal** | m |  |  | n |  | ɲ |  | |
| **Stop** | p     b |  |  | t     d |  |  | k     ɡ | |
| Labialized |  |  |  |  |  |  | kʷ     ɡʷ | |
| **Affricate** |  |  |  |  | tʃ     dʒ |  |  | |
| **Sibilant** |  |  |  | s     z | ʃ     ʒ |  |  | |
| **Fricative** |  | f     v | ð |  |  |  |  | ʁ|
| **Approximant** | w w̃ |  |  |  |  | j j̃ |  | |
| **Tap** |  |  |  | ɾ |  |  |  | |
| **Lateral** |  |  |  | ɫ |  | ʎ |  |  |

###### Vowels

#### Oral vowels

|  | Front | Near-Front | Central | Near-Back | Back |
| :----: | :----: | :----: | :----: | :----: | :----: |
| **Close** | i |  | ɨ |  | u|
|  |  |  |  |  | |
| **Close-Mid** | e |  |  |  | o|
|  |  |  |  |  | |
| **Open-Mid** | ɛ |  |  |  | ɔ|
|  |  |  | ɐ |  | |
| **Open** |  |  | a |  |  |

#### Nasal vowels

|  | Front | Near-Front | Central | Near-Back | Back |
| :----: | :----: | :----: | :----: | :----: | :----: |
| **Close** | ĩ |  |  |  | ũ|
|  |  |  |  |  | |
| **Close-Mid** | ẽ |  |  |  | õ|
|  |  |  |  |  | |
| **Open-Mid** |  |  |  |  | |
|  |  |  | ɐ̃ |  | |
| **Open** |  |  |  |  |  |

#### Details for portuguese_brazil_mfa dictionary and G2P model

- **Source:** wikipron
- **Orthography:** Latin
- **Phone set:** MFA
- **Words:** 213,148
* **Phones:** 40
* **Graphemes:** 85

##### IPA chart

###### Consonants

| Manner | Labial | Labiodental | Alveolar | Alveopalatal | Palatal | Velar | Uvular | Glottal |
| :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: |
| **Nasal** | m |  | n |  |  |  |  | |
| **Stop** | p     b |  | t     d |  |  | k     ɡ |  | |
| Labialized |  |  |  |  |  | kʷ     ɡʷ |  | |
| **Affricate** |  |  |  | tʃ     dʒ |  |  |  | |
| **Sibilant** |  |  | s     z | ʃ     ʒ |  |  |  | |
| **Fricative** |  | f     v |  |  |  |  | ʁ | h|
| **Approximant** | w w̃ |  |  |  | j j̃ |  |  | |
| **Tap** |  |  | ɾ |  |  |  |  | |
| **Lateral** |  |  | l |  | ʎ |  |  |  |

###### Vowels

#### Oral vowels

|  | Front | Near-Front | Central | Near-Back | Back |
| :----: | :----: | :----: | :----: | :----: | :----: |
| **Close** | i |  |  |  | u|
|  |  |  |  |  | |
| **Close-Mid** | e |  |  |  | o|
|  |  |  |  |  | |
| **Open-Mid** | ɛ |  |  |  | ɔ|
|  |  |  | ɐ |  | |
| **Open** |  |  | a |  |  |

#### Nasal vowels

|  | Front | Near-Front | Central | Near-Back | Back |
| :----: | :----: | :----: | :----: | :----: | :----: |
| **Close** | ĩ |  |  |  | ũ|
|  |  |  |  |  | |
| **Close-Mid** | ẽ |  |  |  | õ|
|  |  |  |  |  | |
| **Open-Mid** |  |  |  |  | |
|  |  |  | ɐ̃ |  | |
| **Open** |  |  |  |  |  |

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

#### Brazilian_Portuguese_Conversational_Speech_Corpus

- **Source:** [More Information Needed]
- **License:** [More Information Needed]
- **Dialects:** N/A
- **Number of hours:** 5.80
- **Number of utterances:** 7,293
- **Number of speakers:** 10
  - **Female speakers:** 6
  - **Male speakers:** 4
  - **Unknown speakers:** 0


#### Common Voice Portuguese

- **Source:** https://voice.mozilla.org/en/datasets
- **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
- **Dialects:** brazil, portugal
- **Number of hours:** 111.25
- **Number of utterances:** 95,429
- **Number of speakers:** 2,002
  - **Female speakers:** 58
  - **Male speakers:** 500
  - **Unknown speakers:** 1,444


#### CORAA

- **Source:** [More Information Needed]
- **License:** [More Information Needed]
- **Dialects:** N/A
- **Number of hours:** 289.76
- **Number of utterances:** 400,516
- **Number of speakers:** 77,825
  - **Female speakers:** 0
  - **Male speakers:** 0
  - **Unknown speakers:** 0


#### GlobalPhone Portuguese (Brazilian)

- **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0201/
- **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
- **Dialects:** brazil
- **Number of hours:** 26.26
- **Number of utterances:** 10,344
- **Number of speakers:** 102
  - **Female speakers:** 48
  - **Male speakers:** 53
  - **Unknown speakers:** 1


#### Multilingual LibriSpeech Portuguese

- **Source:** https://openslr.org/94/
- **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)
- **Dialects:** portugal
- **Number of hours:** 168.45
- **Number of utterances:** 39,230
- **Number of speakers:** 62
  - **Female speakers:** 26
  - **Male speakers:** 36
  - **Unknown speakers:** 0


#### Multilingual TEDx Portuguese

- **Source:** https://openslr.org/100/
- **License:** [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/)
- **Dialects:** portugal
- **Number of hours:** 181.68
- **Number of utterances:** 92,172
- **Number of speakers:** 834
  - **Female speakers:** 0
  - **Male speakers:** 0
  - **Unknown speakers:** 834


### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing

Preprocessing include fixes and orthographic standardization to various corpora.


#### Training Hyperparameters

- **Training regime:** [Training configuration](config.yaml)

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

N/A

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

N/A

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

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](https://montreal-forced-aligner.readthedocs.io/).

## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

```
@techreport{mfa_portuguese_mfa_acoustic_2026,
	author={McAuliffe, Michael and Sonderegger, Morgan},
	title={Portuguese MFA acoustic model v3.3.0},
	address={\url{https://huggingface.co/MontrealCorpusTools/portuguese_mfa}},
	year={2026},
	month={Jun},
}
```

**APA:**

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

## Contact

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