This release is a pre-release and may not be stable for production use.
orthography2ipa
orthography2ipa turns the spelling of a language into IPA, and it measures
how languages relate to each other. Each language is a cited JSON spec in
orthography2ipa/data/. A shared engine with no language-specific code turns
the specs into transcriptions and into ranked pronunciation lattices. The
library ships no trained weights.
The registry holds thousands of language codes, from major standard languages to dialects, creoles and reconstructed proto-languages. Most of them are stubs. The language explorer shows each one.
Install
uv pip install --prerelease=allow orthography2ipa
CONTRIBUTING.md sets up a clone of the repository for development.
Quick start
import orthography2ipa
orthography2ipa.transcribe("olá mundo", "pt") # 'oˈla ˈmũdu'
docs/guide/getting_started.md is the tutorial that starts from this call. It covers the dependencies and the optional extras, the two maps of a spec, beam search, language lookup, the command line, plugins and the explorer.
Documentation
| You want to | Read |
|---|---|
| Find a page by task | docs/index.md |
| Rank the readings of an ambiguous spelling, or rescore them | docs/engine/lattice.md |
| Export the lattice as features for a CRF or another ML model | docs/engine/lattice.md |
| Measure how two languages differ in sound, spelling, script, ancestry, time or place | docs/guide/distance.md |
| See the PER, the word count and the provenance of each gold set | docs/evaluation/generated/scoreboard.md |
| Compare the same rows with espeak-ng, epitran and gruut | docs/evaluation/generated/comparison.md |
| Learn what a gold set can prove, and the reliability tiers | docs/evaluation/benchmarks.md |
Read the full --help output |
docs/reference/cli.md |
| Look up an exported name | docs/reference/api.md |
| Read every field of a spec | orthography2ipa/data/SCHEMA.md |
| Write a spec, a citation, a board change or an engine change | docs/contributing/ |
| Learn the repository map, the setup and the hard rules | AGENTS.md |
| Follow the branch model and the commit messages | CONTRIBUTING.md |
| Give a language model a map of the repository | llms.txt |
arbtok (Arabic), tugaphone (Portuguese), g2p_barranquenho and mwl_phonemizer build on this library.
AI transparency
Large language models (Anthropic Claude) wrote most specs, under the direction of a human maintainer. No small project can recruit a native-speaker linguist for thousands of languages. The choice was between an AI-written spec and no spec. Every mapping must trace to a published description: a reference grammar, a peer-reviewed paper or a university dataset. The engine stays language-agnostic, so a spec cannot hide logic. The tests check the structure, and the benchmarks score the output against external data.
A cited spec that a model wrote is still not native-speaker validation, and
the quality tier records that. If you speak a language and its spec is
wrong, open an issue
with a citation or a native-speaker judgment. Corrections have priority over
all other work here.
License
Apache 2.0
1 maintainer
Metadata
1 maintainer
Release files for orthography2ipa 7.111.21a1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| orthography2ipa-7.111.21a1.tar.gz | 5.8 MB | Without provenance | Details for orthography2ipa-7.111.21a1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| orthography2ipa-7.111.21a1-py3-none-any.whl | Python 3 | none | any | Details for orthography2ipa-7.111.21a1-py3-none-any.whl |
Total release size: 15.1 MB
Release files / orthography2ipa-7.111.21a1.tar.gz
| Download URL | orthography2ipa-7.111.21a1.tar.gz |
|---|---|
| Size | 5.8 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3af777d1ac9d864f59dba09696382fcaabda4da5cf2edbc2bed7f3e281e2be37
|
|
BLAKE2b-256 checksum How to use checksums |
19571a9e447c20dacf48ac3740f0ddcd6ea4a0ae6db79599c5d1b49d29a4d9d4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Release files / orthography2ipa-7.111.21a1-py3-none-any.whl
| Download URL | orthography2ipa-7.111.21a1-py3-none-any.whl |
|---|---|
| Size | 9.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0f505686b06c5e7bfe16f37ad065755881a277cbef2be7ea9cd3edfb36e1f601
|
|
BLAKE2b-256 checksum How to use checksums |
e81db3d035268144c5a7e525a847b1e5c349ef0ac4eb3d3d5a06b815b94978d8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Security for orthography2ipa 7.111.21a1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
