Downloads · 30 days
6
19% of all-time downloads
vaghawan/xtts-v2-stage-c-balanced-three-voices-3epoch-1h-bible_tts_speaker-waxalnlp-3-5
xtts-v2-stage-c-balanced-three-voices-3epoch-1h-bible_tts_speaker-waxalnlp-3-5 is a text-to-speech model from vaghawan. Use it when you need text read aloud. It is set up for coqui-tts. The card lists the license as other.
Fine-tuned Coqui XTTS-v2 for Hausa (ha), trained on BibleTTS Hausa (biblettsspeaker) + hausa-speaker-female-waxalnlp-3 + hausa-speaker-female-waxalnlp-5 (balanced ~435 clips/speaker).
Downloads · 30 days
6
19% of all-time downloads
All-time downloads
32
Public
Repo size
5.7 GB
Likes
1
Public
Click a slice to open those files.
.pth5.6 GB · 100%
From the Hugging Face model README
Fine-tuned Coqui XTTS-v2 for Hausa (ha), trained on
BibleTTS Hausa (bible_tts_speaker) + hausa-speaker-female-waxalnlp-3 + hausa-speaker-female-waxalnlp-5 (balanced ~435 clips/speaker).
| File | Purpose |
|---|---|
best_model.pth | Fine-tuned GPT checkpoint (epoch 3) |
config.json | Model config (includes Hausa language) |
vocab.json | Extended Hausa BPE vocabulary |
references/bible_tts_speaker.wav | Speaker reference for bible_tts_speaker |
references/hausa-speaker-female-waxalnlp-3.wav | Speaker reference for hausa-speaker-female-waxalnlp-3 |
references/hausa-speaker-female-waxalnlp-5.wav | Speaker reference for hausa-speaker-female-waxalnlp-5 |
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 |
pip install -r requirements.txt
cp config.env.example config.env
python infer.py --model-dir . --speaker-wav references/bible_tts_speaker.wav
# Single line:
python infer.py --model-dir . --text "Ina kwana." --speaker-wav references/bible_tts_speaker.wav --out outputs/out.wav
python infer.py --model-dir . --all-speakers --out-dir outputs/samples
ha)bible_tts_speaker, hausa-speaker-female-waxalnlp-3, hausa-speaker-female-waxalnlp-5XTTS-v2 uses the Coqui Public Model License. Check each dataset license before redistribution.