Downloads · 30 days
13
12% of all-time downloads
okyeame-tts-xtts-v5
Josephus67/okyeame-tts-xtts-v5
okyeame-tts-xtts-v5 is a machine learning model from Josephus67. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for coqui-tts. The card lists the license as apache-2.0.
Fine-tuned XTTS v2 model for Ghanaian-accented English speech synthesis.
All-time downloads
111
Public
Repo size
5.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth5.8 GB · 100%
At a glance
- Library
- coqui-tts
- License
- apache-2.0
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- a2be139a
Spaces
Model card
From the Hugging Face model README
Okyeame TTS — Ghanaian English XTTS v2 Fine-tune
Fine-tuned XTTS v2 model for Ghanaian-accented English speech synthesis.
Usage
from huggingface_hub import snapshot_download
from TTS.api import TTS
model_dir = snapshot_download("Josephus67/okyeame-tts-xtts-v2")
tts = TTS()
tts.load_tts_model_by_path(
model_path=f"{model_dir}/model.pth",
config_path=f"{model_dir}/config.json"
)
tts.tts_to_file(
text="Good morning, how are you doing today?",
speaker_wav=f"{model_dir}/reference.wav",
language="en",
file_path="output.wav",
split_sentences=True
)
Training Data
Trained on the Ghana English ASR 2700hrs dataset.
Model Details
- Base model: XTTS v2 (Coqui)
- Fine-tuning: GPT decoder layers
- Sample rate: 22050 Hz (internal), 24000 Hz (output)
- Library
- coqui-tts
- License
- apache-2.0
- Languages
- en
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026