Skip to main content

Tokenizer fertility, cost, and multi-turn context-budget analyzer for low-resource Asian languages.

Project description

asia-fertility 🌏

The hidden multilingual tax in your tokenizer — measured before you deploy.

CI License Python

Status: v0.2 under active construction. See ROADMAP.md and the per-phase specs in tasks/.

asia-fertility measures the structural cost penalty that LLM tokenizers impose on lower-resource Asian languages. The same content can cost up to 11× more tokens in Burmese than in English on a frontier tokenizer — silent inflation of API bills, smaller usable context windows, and fewer in-context examples.

Quickstart (once v0.3 ships)

pip install "asia-fertility[oai]"
asia-fertility reproduce

What's currently usable

  • v0.1 Python prototype: legacy_v01/fertiscope/ (EN↔VI only, CLI).
  • Live Next.js web demo: fertiscope.vercel.app.
  • 41 implementation specs: tasks/.

License

MIT © 2026 Antoine Pedretti. Bundled FLORES-200 data: CC-BY-SA 4.0 (Meta NLLB).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

asia_fertility-0.2.0.tar.gz (37.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

asia_fertility-0.2.0-py3-none-any.whl (50.8 kB view details)

Uploaded Python 3

File details

Details for the file asia_fertility-0.2.0.tar.gz.

File metadata

  • Download URL: asia_fertility-0.2.0.tar.gz
  • Upload date:
  • Size: 37.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for asia_fertility-0.2.0.tar.gz
Algorithm Hash digest
SHA256 b2bb825b9d2555a80110f1686e1bacd3b212697a81e8fd1d9bfeb63a2bfbeab5
MD5 15bd0260b021b7ca178c820d8289f69a
BLAKE2b-256 89ffab0312dc39da24987cd22d20e0d7dfa9150a6775cbe0283c6ac139d22c88

See more details on using hashes here.

Provenance

The following attestation bundles were made for asia_fertility-0.2.0.tar.gz:

Publisher: publish.yml on Helmo21/asia-fertility

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file asia_fertility-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: asia_fertility-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 50.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for asia_fertility-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 73739ebc4d676539c439347a8c966827d2a3fedc71b852ee94bb2fa24e186970
MD5 61e8c3ff4650ffbde76122052e6a48f0
BLAKE2b-256 89527a194fc93b919c59f621bdc089e1368e77a2d6e3e9db4cbde029ea8224d7

See more details on using hashes here.

Provenance

The following attestation bundles were made for asia_fertility-0.2.0-py3-none-any.whl:

Publisher: publish.yml on Helmo21/asia-fertility

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page