| --- |
| language: |
| - en |
| pipeline_tag: other |
| library_name: montreal-forced-aligner |
| tags: |
| - montreal-forced-aligner |
| - forced-alignment |
| license: cc-by-4.0 |
| --- |
| # Model Card for english_us_arpa |
|
|
| <!-- Provide a quick summary of what the model is/does. --> |
|
|
| This MFA model is for aligning US English using the ARPAbet phone set. |
|
|
| - [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):** English |
| - **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 US English. Other varieties of English (e.g. UK, Indian, Nigerian Englishes) may have inconsistent performance. 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 of US English. |
| |
| ## 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 US English. 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 english_us_arpa dictionary and G2P model |
|
|
| - **Source:** wikipron |
| - **Orthography:** Latin |
| - **Phone set:** ARPA |
| - **Words:** 266,823 |
| * **Phones:** 39 |
| * **Graphemes:** 35 |
|
|
| ##### IPA chart |
|
|
| ###### Consonants |
|
|
| | Manner | Labial | Labiodental | Dental | Alveolar | Alveopalatal | Palatal | Velar | Glottal | |
| | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: | |
| | **Nasal** | M | | | N | | | NG | | |
| | **Stop** | P B | | | T D | | | K G | | |
| | **Affricate** | | | | | CH JH | | | | |
| | **Sibilant** | | | | S Z | SH ZH | | | | |
| | **Fricative** | | F V | TH DH | | | | | HH| |
| | **Approximant** | W | | | R | | Y | | | |
| | **Lateral** | | | | L | | | | | |
|
|
| ###### Vowels |
|
|
| | | Front | Near-Front | Central | Near-Back | Back | |
| | :----: | :----: | :----: | :----: | :----: | :----: | |
| | **Close** | IY | | UW | | | |
| | | | IH | | UH | | |
| | **Close-Mid** | EY | | | | OW| |
| | | | | AH | | | |
| | **Open-Mid** | EH | | | | | |
| | | AE | | ER | | | |
| | **Open** | | | | | AA AO | |
|
|
| ##### Diphthongs |
| * OY |
| * AY |
| * AW |
|
|
|
|
| ## 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. --> |
|
|
| #### LibriSpeech English |
|
|
| - **Source:** https://openslr.org/12/ |
| - **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) |
| - **Dialects:** us |
| - **Number of hours:** 982.10 |
| - **Number of utterances:** 292,367 |
| - **Number of speakers:** 2,484 |
| - **Female speakers:** 1,283 |
| - **Male speakers:** 1,201 |
| - **Unknown speakers:** 0 |
|
|
|
|
| ### 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_english_us_arpa_acoustic_2026, |
| author={McAuliffe, Michael and Sonderegger, Morgan}, |
| title={English (US) ARPA acoustic model v3.3.0}, |
| address={\url{https://huggingface.co/MontrealCorpusTools/english_us_arpa}}, |
| year={2026}, |
| month={Jun}, |
| } |
| ``` |
|
|
| **APA:** |
|
|
| ``` |
| McAuliffe, M. & Sonderegger, M. (2026). English (US) ARPA acoustic model v3.3.0. Available at https://huggingface.co/MontrealCorpusTools/english_us_arpa. |
| ``` |
|
|
| ## Contact |
|
|
| For questions and issues, please file an issue either for this model at https://huggingface.co/MontrealCorpusTools/english_us_arpa/discussions or for larger MFA issues at https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner/issues. |
