luxembourgish_mfa

Model Card for Model ID

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

• Model details
• Uses
• Performance Factors
• Dictionary Details
• Training Details
• Evaluation
• Contact

Model Details

Model Description

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

Luxembourgish MFA acoustic model (lb_acoustic_lux) with pronunciation dictionary and G2P for forced alignment.

• Developed by: ['Peter Gilles', 'University of Luxembourg']
• Funded by: University of Luxembourg
• Model type: Montreal Forced Aligner model
• Language(s) (NLP): Luxembourgish
• 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. -->

Forced alignment of Luxembourgish speech using MFA align_hf.

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.

Bias, Risks, and Limitations

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

Best on Luxembourgish varieties similar to the training data.

Recommendations

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

Adapt the model when aligning substantially different varieties.

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:

mfa align_hf CORPUS pgilles/luxembourgish_mfa OUTPUT \
  --dialect luxembourgish --use_g2p

Dictionary Details

Details for luxembourgish_run6 dictionary and G2P model

• Source: wikipron
• Orthography: [More Information Needed]
• Phone set: [More Information Needed]
• Words: 58,731

• Phones: 70
• Graphemes: 59

IPA chart

Consonants

Vowels

Other

• ð
• ɲ
• œː
• p
• uː
• y
• h
• u
• n
• ɔ
• ɕ
• ɥ
• æːɪ
• o
• yː
• ɑɪ
• ɹ
• s
• mː
• tʃ
• ɜɪ
• ŋ
• f
• iː
• ʒ
• æl
• l
• b
• iə
• ɛː
• uə
• œ
• ən
• t
• dʒ
• øː
• əʊ
• k
• aː
• j
• ɛ
• χ
• ɑː
• i
• e
• ɔː
• w
• oː
• a
• oɪ
• eː
• v
• ts
• ʁ
• ɔɪ
• ɡ
• d̥ː
• ʑ
• m
• θ
• ø
• ɑ
• z
• æː
• ɑʊ
• ʀ
• dz
• d
• ʃ
• æːʊ

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. -->

lb_acoustic_lux

• Source: [More Information Needed]
• License: cc-by-4.0
• Dialects: N/A
• Number of hours: 67.53
• Number of utterances: 88,183
• Number of speakers: 7
  • Female speakers: 0
  • Male speakers: 0
  • 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

Standard MFA corpus preparation for Luxembourgish speech.

Training Hyperparameters

• Training regime: Training configuration

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. -->

[More Information Needed]

Factors

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

[More Information Needed]

Metrics

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

[More Information Needed]

Results

[More Information Needed]

Summary

Technical Specifications

Model Architecture and Objective

HMM-GMM model

Software

Montreal Forced Aligner 3.4

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:

[More Information Needed]

APA:

[More Information Needed]

Contact

[More Information Needed]