canto-tts

Cantonese Hong Kong Text-to-Speech · CPU-first · Apache-2.0

An open-source Cantonese (Hong Kong) text-to-speech SDK. Runs on CPU via ONNX Runtime — no GPU required. Fine-tuned from MOSS-TTS-Nano (0.1 B params, GPT-2 backbone, Apache-2.0, by OpenMOSS).

Weights published — CER 11.82% / tone accuracy 84.22% / code-switch CER 13.87% on a 100-sentence gate set (N=5 repeat eval). Single default voice only — no voice cloning, no voice selection (yet). PyPI package not published yet — install from source for now; see the GitHub repo for current status.

Install

git clone https://github.com/typangaa/canto-tts.git && cd canto-tts && pip install -e .

Quickstart

from canto_tts import CantoTTS

tts = CantoTTS()  # auto-downloads typangaa/canto-tts-nano from HuggingFace on first use
tts.synthesize("多謝晒，今日天氣幾好。", "hello.wav")
print("Saved to hello.wav")

# English code-switching works too
tts.synthesize("我哋一齊去 IFC food court 食飯。", "codeswitching.wav")

Weights auto-download from HuggingFace and cache via the Hub (~/.cache/huggingface/hub/).

Quality Modes (opt-in)

Two opt-in quality= modes trade extra compute for a more reliable draw, without touching the model:

tts.synthesize(text, "out.wav", quality="duration_filter", max_attempts=3)   # no extra deps
tts.synthesize(text, "out.wav", quality="best_of_n", best_of_n=4)            # needs canto-tts[quality]

quality="best_of_n" reranks N draws by ASR character-error-rate; pass asr_backend="sensevoice" (needs canto-tts[quality-sensevoice]) for ~7x faster reranking at a small accuracy cost. Full writeup: GitHub README.

Limitations


Quality	CER 11.82% / tone accuracy 84.22% / code-switch CER 13.87% (N=5 repeat, 100-sentence gate set).
Voice	Single default voice. No voice cloning, no voice selection (yet).
Language	Cantonese (Hong Kong) + English code-switching only. No Mandarin.
Training data	Privately sourced — not released (copyright), regardless of weight status.
Weights	✅ Published — huggingface.co/typangaa/canto-tts-nano.

Model & License

Base model: MOSS-TTS-Nano by OpenMOSS
Weights: published at huggingface.co/typangaa/canto-tts-nano
License: Apache-2.0 (inherited from MOSS-TTS-Nano)

Full Documentation

Full README, CLI docs, Docker self-hosting, and deployment guide: https://github.com/typangaa/canto-tts

Download files

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

Source Distribution

canto_tts-0.1.0.tar.gz (55.5 kB view details)

Uploaded Jul 28, 2026 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

canto_tts-0.1.0-py3-none-any.whl (55.1 kB view details)

Uploaded Jul 28, 2026 Python 3

File details

Details for the file canto_tts-0.1.0.tar.gz.

File metadata

Download URL: canto_tts-0.1.0.tar.gz
Upload date: Jul 28, 2026
Size: 55.5 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for canto_tts-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`dc353e61d50f60727184dde9346a48148aa52a4ec610cd4dd71149e23ab02782`
MD5	`c7e4aba66e1dd9defc43c05d9c2ff352`
BLAKE2b-256	`620ac79db1d5da0f61b1943ac3b6b3abaebc5e5b37bbd3b2c9bc193017c0db18`

See more details on using hashes here.

Provenance

The following attestation bundles were made for canto_tts-0.1.0.tar.gz:

Publisher: publish.yml on typangaa/canto-tts

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: canto_tts-0.1.0.tar.gz
- Subject digest: dc353e61d50f60727184dde9346a48148aa52a4ec610cd4dd71149e23ab02782
- Sigstore transparency entry: 2267757950
- Sigstore integration time: Jul 28, 2026
Source repository:
- Permalink: typangaa/canto-tts@58109c407dfb309f5468e2cff8568c762554d6d5
- Branch / Tag: refs/tags/v0.1.0
- Owner: https://github.com/typangaa
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@58109c407dfb309f5468e2cff8568c762554d6d5
- Trigger Event: push