Downloads · 30 days
13
30% of all-time downloads
lfm2-arabic-tts
azeddinShr/lfm2-arabic-tts
lfm2-arabic-tts is a machine learning model from azeddinShr. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Training: Stage 1 (Depthformer only), 10 epochs, Audio loss: 0.058
All-time downloads
43
Public
Parameters
1.2B
5.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.7 GB · 59%
At a glance
- Model type
- lfm2
- Access
- Public
- Created
- Jan 10, 2026
- Updated
- Jan 10, 2026
- SHA
- 329114c2
Model card
From the Hugging Face model README
LFM2-Audio Arabic TTS
Loading
from liquid_audio import LFM2AudioModel, LFM2AudioProcessor
import torch
# Load base model and processor
processor = LFM2AudioProcessor.from_pretrained("LiquidAI/LFM2-Audio-1.5B")
model = LFM2AudioModel.from_pretrained("LiquidAI/LFM2-Audio-1.5B").eval().cuda()
# Load fine-tuned weights
state_dict = torch.load("pytorch_model.bin")
model.load_state_dict(state_dict)
Training: Stage 1 (Depthformer only), 10 epochs, Audio loss: 0.058
- Type
- lfm2
- Created
- Jan 10, 2026
- Updated
- Jan 10, 2026