Code-Quasar/voxcpm-tn

VoxCPM2 fine-tuned for Tunisian Derja.

• base: openbmb/VoxCPM2 (2B, tokenizer-free, 48 kHz)
• method: full fine-tuning, 147 steps
• data: ~? h Tunisian read speech, 16 kHz mono

Important: the dialect tag

Every training transcript was prefixed with (Tunisian Dialect), so untagged text is out of distribution. Always prefix it:

from voxcpm import VoxCPM

model = VoxCPM.from_pretrained("Code-Quasar/voxcpm-tn", load_denoiser=False)
wav = model.generate(text="(Tunisian Dialect) عسلامة، شنوة أحوالك اليوم؟")

import soundfile as sf
sf.write("out.wav", wav, 48000)

On a GPU with under ~8 GB, disable compilation:

import os
os.environ["TORCHDYNAMO_DISABLE"] = "1"

Limitations

Trained on a small corpus of read speech, so expect limited prosodic range and weaker long-form phrasing. Derived from source corpora with their own licence terms; the voices belong to real speakers.