travis-moore/sema-sauti-v2

Sema Sauti v2

Sema's Ghanaian voice: one cloned voice that speaks Twi, Nigerian and Ghanaian Pidgin, and English in a single model. Give it a few seconds of reference audio and it speaks all three in that voice.

Built under Sema by Angelo Asante.

Sema Sauti v2 is the fully-trained build: the final step of the run, with more passes over the data.

Hear it

Reference-cloned voices (exaggeration=0.5, cfg_weight=0.5).

Clip	What it is
	Twi, author's voice: “Me da wo ase paa, Onyankopɔn nhyira wo.”
	Twi–English code-switch: “Ɛnnɛ deɛ the meeting go start at nine o'clock.”
	Nigerian Pidgin, Nigerian voice: “Abeg make you no vex, I go explain everything.”
	Ghanaian Pidgin, author's voice: “Chale, the game yesterday be mad, you for see am.”
	English, author's voice.
	French — one of the languages the model also speaks.
	Swahili — another language it carries.

Languages

Three are trained targets — English, Twi/Akan, and Nigerian + Ghanaian Pidgin. Alongside them the model speaks a set of other languages it carried through training. We checked the whole set with a read-back test: one sentence per language, transcribed by Whisper large-v3 and scored as Character Error Rate (lower is better; ~8–10 is the floor because the scorer writes "9" for "nine").

Trained targets

Language	code
English	en
Twi / Akan	tw
Nigerian & Ghanaian Pidgin	pcm

Also spoken (carried through training, Latin-script):

Language	code	read-back CER
Dutch	nl	7.5
Portuguese	pt	8.9
German	de	13.0
Turkish	tr	13.5
Swahili	sw	15.0
Spanish	es	19.1
Norwegian	no	19.4
Malay	ms	19.6
Italian	it	20.0
French	fr	25.5
Danish	da	28.9
Swedish	sv	35.1

Numbers are for this checkpoint; these languages are intelligible on both Sema Sauti v1 and v2, a few points stronger on one or the other.

Not supported: Arabic, Chinese, Greek, Hebrew, Hindi, Japanese, Korean and Russian — these scripts aren't in the model's tokenizer, so it can't render them. Finnish and Polish come through only partially.

How we built it

• We fine-tuned only the pronunciation stage — the part that carries accent, rhythm and pronunciation — on several hours of Twi and Nigerian Pidgin speech, many speakers, short clips, with Ghanaian Pidgin and African-accented English in the mix.
• The voice encoder and vocoder are left frozen, so the model keeps clean zero-shot voice cloning and clean English while gaining natural Twi and Pidgin.

The shipped weights are the final step 5124. The evaluation-loss curve bottoms a little earlier (step 3300 = v1); v2 trades a hair of that for more time on the data.

Use

from huggingface_hub import snapshot_download
from chatterbox.tts import ChatterboxTTS
import torchaudio

d = snapshot_download("travis-moore/sema-sauti-v2", token=HF_TOKEN)
model = ChatterboxTTS.from_local(d, device="cuda")
wav = model.generate(
    "Me da wo ase paa. Chale, the meeting go start at nine o'clock.",
    audio_prompt_path="reference.wav",   # 7-10 s of the target voice
    exaggeration=0.5, cfg_weight=0.5,
)
torchaudio.save("out.wav", wav, model.sr)

The folder is a self-contained model directory; it loads with ChatterboxTTS.from_local.

Limitations

• Twi and Nigerian Pidgin are strongest; Ghanaian and Cameroonian Pidgin come through by transfer and are lighter. A matching voice reference helps.
• The "also spoken" languages are ability the model retained, not a dedicated fine-tune — expect a light accent and occasional slips.
• Numbers, acronyms and dates are a known soft spot.
• Clone only voices you have the right to use; outputs carry an inaudible watermark.

Safety

This model clones a voice from a few seconds of audio. Use it only on voices you have the right to use. Impersonating a real person without their consent, deception and fraud are against the intent of this release; disclose synthetic audio where a listener could reasonably be misled.

Versions

Version	Checkpoint	Notes
sema-sauti-v1	step 3300	lowest read-back error; recommended
sema-sauti-v2	step 5124	full training run, final step

---

Fine-tuned from ResembleAI/chatterbox (MIT).