Downloads · 30 days
3
4% of all-time downloads
dicksonsarpong9/voxcpm_nigeria_accent
voxcpm_nigeria_accent is a text-to-speech model from dicksonsarpong9. Use it when you need text read aloud. It is set up for voxcpm. The card lists the license as apache-2.0.
VoxCPM0.5B fine-tuned on Nigerian accent data.
Downloads · 30 days
3
4% of all-time downloads
All-time downloads
82
Public
Repo size
1.7 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 78%
From the Hugging Face model README
VoxCPM0.5B fine-tuned on Nigerian accent data.
from voxcpm.core import VoxCPM
from voxcpm.model.voxcpm import LoRAConfig
import json
with open('lora_config.json') as f:
lora_info = json.load(f)
lora_cfg = LoRAConfig(**lora_info['lora_config'])
model = VoxCPM.from_pretrained(
hf_model_id='dicksonsarpong9/voxcpm_nigeria_accent',
lora_config=lora_cfg,
lora_weights_path='lora_weights.safetensors'
)
audio = model.generate(text='Hello!')