hama on-device NLP

There's a pronunciation model in this tab.

On-device language processing in Python, Node, and the browser

Run the demo Browse the docs 
uv pip install hama
from hama import G2PModel

model = G2PModel()
result = model.predict(
    "I saw her duck.",
    preserve_literals="punct",
)
print(result.ipa)
print(result.display_ipa)

Targets

Python · TypeScript

Browser and server runtimes.

Engine

~39 KB

Self-contained WASM. No onnxruntime.

Latency

~24× real-time

Phoneme ASR on a laptop CPU.

Cheap. Fast. Accurate. Pick three.

Twelve languages, zero servers.

Tasks

Text → IPA

Available

Audio → IPA

Available

IPA → Text

Available

Audio → Text

(Speech recognition)

Available

Text → Embeddings

Coming soon

Features

Character-level alignments

Every output phoneme maps back to the input characters that produced it.

Code-mixed input

Sentences that mix languages and scripts convert in a single call.

One model set, three runtimes

Python, Node, and the browser run the same hand-written Zig engine and return the same outputs.

Apache 2.0

Permissive license for commercial and embedded use.

Supported languages

IPA reference
English French German Italian Japanese Korean Portuguese Spanish Dutch Thai (Central) Chinese (Simplified) Chinese (Traditional)

Try it out

Speech → text (opens in a new tab)

Try sample inputs or type your own text.

Loading model weights in the browser… (Inference runs locally.)
Display IPA

—

Alignments

Built on the same model: Make AI say your name correctly, a transcript fixer that matches names by pronunciation.

Blog

View all

hama v1.6.0: alignments for ASR and P2G

6/28/2026

hama v1.5.0: phoneme-to-grapheme, a SIMD engine, and fp16 weights

6/27/2026

hama v1.4.0: ONNX Runtime is gone, replaced by a Zig engine

6/24/2026

Built with Mozilla Common Voice

hama's phoneme recognizer is trained in part on Mozilla Common Voice. Why community voice data matters for on-device speech models.

6/10/2026

hama v1.3.13: Faster pronunciation matching

6/10/2026

Documentation

Browse docs

Getting started

Introduction

Overview, guiding principles, and supported languages.

Getting started

Installation

Set up Python and TypeScript runtimes for development or deployment.

Reference

APIs

Detailed reference for model classes and helper functions.

Reference

IPA Reference

Practical IPA symbol table and interpretation guide for hama outputs.

Sponsor the models your browser just ran.

Sponsorship pays for training compute, model maintenance, and documentation.

Sponsor on GitHub Sponsor list