---
license: apache-2.0
language:
- de
pipeline_tag: text-to-speech
library_name: sherpa-onnx
base_model: Godelaune/Kokoro-82M-ONNX-German-Martin
tags:
- onnx
- kokoro
- sherpa-onnx
- text-to-speech
- german
- single-speaker
---

# Kokoro German "Martin" — sherpa-onnx package

The German Kokoro voice **Martin**, repackaged so it loads and runs in
**[sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx)** for fully offline, on-device German
text-to-speech.

This is a **repackaging, not a retraining** — the weights are untouched. The only changes are the
metadata and file layout sherpa-onnx needs in order to load a Kokoro model at all.

## Why the repackaging is needed

sherpa-onnx's Kokoro TTS reads its configuration out of the ONNX file's **metadata** (model type,
sample rate, speaker table, style dimensions, …) to know how to run the model, and it expects the
speaker style vectors as a single flat **`voices.bin`**. The upstream Martin export provides
neither — the ONNX carries no sherpa-onnx metadata, and the voice ships as a NumPy `.npz` — so
sherpa-onnx cannot load it directly. This package fixes exactly that:

- **injects the sherpa-onnx Kokoro metadata** into the ONNX (`model_type=kokoro`,
  `sample_rate=24000`, `style_dim=510,1,256`, `n_speakers=1`, `id2speaker=0->martin`, …), copied
  from k2-fsa's own Kokoro release schema, and
- **converts** the voice `.npz` (one `(510,1,256)` float32 array) into the flat little-endian
  `voices.bin` sherpa expects (522 240 bytes).

The result loads and synthesizes in sherpa-onnx with the weights unchanged.

## What's in the archive

`kokoro-de-martin.tar.bz2`:

- `model.onnx` — the Martin ONNX with sherpa-onnx Kokoro metadata injected
- `voices.bin` — the voice style vector (510×1×256 float32)
- `tokens.txt` and `espeak-ng-data/` — from the k2-fsa sherpa-onnx Kokoro release

## Known limitation

sherpa-onnx phonemizes German with espeak-ng / piper-phonemize, whose G2P emits the German
**ich-laut /ç/ decomposed** (`c` + combining cedilla, U+0327); the precomposed Kokoro token set
drops it, so `ich`, `nicht` and `-lich` / `-ig` words don't render cleanly from raw text. This is
a property of the sherpa-onnx Kokoro G2P pipeline, not of the voice, and affects any Kokoro voice
run this way. The usual sherpa workaround applies: supply the affected words through a lexicon so
their phonemes bypass the runtime G2P.

## How it was built

Reproducibly, by a small build chain: fetch the upstream Martin ONNX + voice `.npz` and k2-fsa's
base Kokoro release (for the metadata schema, `tokens.txt`, and `espeak-ng-data/`), inject the
metadata, convert the `.npz` to `voices.bin`, and assemble the archive. A verify step then loads
the result in sherpa-onnx and synthesizes a German clip to confirm it works before publishing.

## Provenance & license

**Apache-2.0**, inherited from upstream. The weights are unchanged from the source fine-tune:

- ONNX source: [Godelaune/Kokoro-82M-ONNX-German-Martin](https://huggingface.co/Godelaune/Kokoro-82M-ONNX-German-Martin)
- Fine-tune: [kikiri-tts/kikiri-german-martin](https://huggingface.co/kikiri-tts/kikiri-german-martin)
  (Martin Harbecke voice, StyleTTS2)
- Architecture: [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M)
- `tokens.txt` + `espeak-ng-data/`: k2-fsa sherpa-onnx Kokoro release

## Usage

Extract `kokoro-de-martin.tar.bz2` and point sherpa-onnx's Kokoro config at `model.onnx`,
`voices.bin`, `tokens.txt`, and `espeak-ng-data/` with `lang=de`.