MétaCan
Menu
Back to cohort
Record W4200300291 · doi:10.21105/joss.03958

Phonemizer: Text to Phones Transcription for Multiple Languages in Python

2021· article· en· W4200300291 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueThe Journal of Open Source Software · 2021
Typearticle
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsnot available
FundersAgence Nationale de la RechercheCanadian Institute for Advanced ResearchMicrosoft Research
KeywordsPython (programming language)Computer scienceTranscription (linguistics)Programming languageWorld Wide WebLinguisticsPhilosophy

Abstract

fetched live from OpenAlex

Phones are elementary sounds the speech is made of, on which syllables and words are built.The transcription of texts from their orthographic form into a phonetic alphabet is an important requirement in various applications related to speech and language processing, for instance for text to speech systems.Phonemizer is a Python package addressing precisely this issue: it transcribes a text from its orthographic representation into a phonetic one.The package is user-friendly and exposes a single high-level phonemize function, a lower lovel API, and is also available as a command-line interface.It supports about a hundred different languages and provides end-user functionalities such as punctuation preservation, phones accentuation, tokenization at phone/syllable/word levels, as well as parallel processing of large input texts.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.933
Threshold uncertainty score0.275

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.035
GPT teacher head0.302
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it