VoxCPM2-Yoruba

VoxCPM2-Yoruba (Experimental)

⚠️ Experimental research model. An early full fine-tune of VoxCPM2 for Yoruba and Yoruba–English code-switched speech. Promising but not production-grade — expect occasional mispronunciations, tone errors, and artifacts.

A Yoruba text-to-speech model from LyngualLabs, full fine-tuned from openbmb/VoxCPM2 — a 2B, tokenizer-free, voice-cloning TTS. It speaks Yoruba in native script, including code-switching with English, with no G2P / espeak / language tags.

Why

VoxCPM2 ships 30 languages but not Yoruba. Adapting a new language is a high-rank change, so LoRA plateaued; this is the full fine-tune (all 2B weights) that installs Yoruba phonetics and tones.

Training data

Training

• Method: full fine-tuning (all weights), not LoRA
• Base: openbmb/VoxCPM2 (2B) · Steps: 5000 (selected at the validation-loss minimum)
• LR: 1e-5 cosine · Effective batch: 32 (bs 4 × grad-accum 8) · bf16
• Hardware: single NVIDIA RTX 6000 Blackwell (96 GB)

Usage

A voice-cloning model: give a short reference clip + its transcript, and it speaks your text in that voice — or use voice-design (a text description, no reference).

# pip install git+https://github.com/OpenBMB/VoxCPM.git
from huggingface_hub import snapshot_download
from voxcpm import VoxCPM
import soundfile as sf

model_dir = snapshot_download("LyngualLabs/VoxCPM2-Yoruba")
model = VoxCPM.from_pretrained(model_dir, load_denoiser=False)

# --- voice cloning: a reference clip + its exact transcript ---
wav = model.generate(
    text="Mo fẹ́ learn how to code, ṣùgbọ́n mi ò mọ programming language wo ló make sense.",
    prompt_wav_path="reference.wav",
    prompt_text="Ìròyìn ti sọ pé the government will ensure electricity tariff goes down ní January.",
    cfg_value=2.0,
    inference_timesteps=22,
)
sf.write("output.wav", wav, model.tts_model.sample_rate)

# --- or voice-design (no reference): prepend a voice description in parentheses ---
wav = model.generate(
    text="(A young Nigerian woman, clear voice) Ẹ kú àárọ̀, ẹ jọ̀ọ́ ẹ jẹ́ ká bẹ̀rẹ̀ ìpàdé.",
    cfg_value=2.0,
    inference_timesteps=22,
)
sf.write("voice_design.wav", wav, model.tts_model.sample_rate)

Tips: raise inference_timesteps (20–25) for smoother audio; cfg_value higher sticks closer to the reference.

Audio samples

Synthesized by this model (step 5000) — code-switched Yoruba–English, cloned from a single reference voice.

If rain falls tomorrow, jọ̀ọ́ rántí láti mú umbrella àti raincoat. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/samples/sample_4.wav"></audio>

Ìròyìn ti sọ pé the government will ensure electricity tariff goes down ní January. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/samples/sample_5.wav"></audio>

Ẹ̀gbọ́n mi tó ń ṣiṣẹ́ ní bank ti gba promotion, we're all so so happy. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/samples/sample_6.wav"></audio>

Mo fẹ́ learn how to code, ṣùgbọ́n mi ò mọ programming language wo ló make sense. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/samples/sample_7.wav"></audio>

Wọ́n ní ìpàdé ní hotel tó wà ní Victoria Island, kì í ṣe ní office wa. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/samples/sample_8.wav"></audio>

Diverse voices

The same model can render different voices via voice-design (a text description, no reference clip):

Woman — Wọ́n ní ìpàdé ní hotel tó wà ní Victoria Island, kì í ṣe ní office wa. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/voices/woman.wav"></audio>

Young man — Mo fẹ́ learn how to code, ṣùgbọ́n mi ò mọ programming language wo ló make sense. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/voices/youngman.wav"></audio>

Energetic — Ẹ̀gbọ́n mi tó ń ṣiṣẹ́ ní bank ti gba promotion, we're all so so happy. <audio controls src="https://huggingface.co/LyngualLabs/VoxCPM2-Yoruba/resolve/main/voices/energetic.wav"></audio>

Limitations

• Experimental — not production quality; errors increase on long / number-heavy text.
• Multi-speaker training — use a reference clip for a consistent voice.
• Specialized to Yoruba — full FT trades the base's other-language ability for Yoruba.
• Reflects the spontaneous + code-switched style of its training data.

Credits & license

Base: OpenBMB/VoxCPM2 (Apache-2.0) · Data: YECS (LyngualLabs), WAXAL (google/WaxalNLP) · Part of the WAXAL speech effort · Apache-2.0.