Downloads · 30 days
8
14% of all-time downloads
voxcpm-spanish-lora-18k
ipsilondev/voxcpm-spanish-lora-18k
voxcpm-spanish-lora-18k is a text-to-speech model from ipsilondev. Use it when you need text read aloud. The card lists the license as apache-2.0.
This is a LoRA adapter for VoxCPM (MiniCPM-o-2.6 based TTS) fine-tuned on Spanish audio data.
All-time downloads
59
Public
Parameters
802M
3.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 87%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Access
- Public
- Created
- Jan 28, 2026
- Updated
- Feb 15, 2026
- SHA
- d62bae44
Base models
Model card
From the Hugging Face model README
VoxCPM Spanish LoRA (18k Steps)
This is a LoRA adapter for VoxCPM (MiniCPM-o-2.6 based TTS) fine-tuned on Spanish audio data.
Training Details
- Base Model: VoxCPM-1.5 (MiniCPM-o-2.6)
- Dataset: Spanish General + Common Voice
- Steps: 18,000
- Type: LoRA Adapter
Usage
Use the included inference.py script (renamed from test_voxcpm_lora_infer.py) to test this adapter.
python inference.py --checkpoint_path . --text "Hola, esto es una prueba."
- Task
- Text-to-Speech
- License
- apache-2.0
- Languages
- es
- Created
- Jan 28, 2026
- Updated
- Feb 15, 2026