vaghawan/xtts-v2-single-speaker-waxalnlp-speaker3-epoch10

XTTS-v2 Hausa — single speaker (WaxalNLP speaker 3, 10 epochs)

Fine-tuned Coqui XTTS-v2 for Hausa (ha), trained on vaghawan/hausa-tts-24khz-waxalnlp-3-clean (speaker hausa_fe_waxal_nlp_3).

Files

File	Purpose
best_model.pth	Fine-tuned GPT checkpoint (epoch 10)
config.json	Model config (includes Hausa language)
vocab.json	Extended Hausa BPE vocabulary
references/hausa_fe_waxal_nlp_3.wav	Default speaker reference for voice cloning
infer.py	Inference script
xtts_hausa_patch.py	Required Hausa runtime patches
env_config.py	Config loader
config.env.example	Example settings (copy to config.env)
samples.txt	Default eval sentences
requirements.txt	Python dependencies

Quick start

pip install -r requirements.txt
cp config.env.example config.env
# Edit config.env if needed (HF token optional for this repo)

python infer.py --model-dir . --speaker-wav references/hausa_fe_waxal_nlp_3.wav

# Single line:
python infer.py --model-dir . --text "Ina kwana." --speaker-wav references/hausa_fe_waxal_nlp_3.wav --out outputs/out.wav

Training details

• Base model: Coqui XTTS-v2
• Dataset: WaxalNLP Hausa TTS 24 kHz (speaker 3)
• Epochs: 10
• Language: Hausa (ha)

License

XTTS-v2 uses the Coqui Public Model License. Check the WaxalNLP dataset license before redistribution.