---
license: apache-2.0
language:
- id
library_name: voxcpm
tags:
- tts
- text-to-speech
- voice-cloning
- lora
- voxcpm
- indonesian
base_model: openbmb/VoxCPM1.5
---

# VoxCPM LoRA - Indonesian Female Voice v2

LoRA adapter for [VoxCPM 1.5](https://huggingface.co/openbmb/VoxCPM1.5) fine-tuned for natural Indonesian female speech.

**v2 improvements:** Higher capacity LoRA (r=64), trained on 400 samples (vs 112 in v1), lower final loss.

## Model Details

| Property | Value |
|----------|-------|
| Base model | openbmb/VoxCPM1.5 (800M params) |
| LoRA rank (r) | 64 |
| LoRA alpha | 32 |
| Training steps | 3500 |
| Training samples | 400 clips |
| Final loss | 0.750 |
| Sample rate | 44.1 kHz |

## Installation

Safetensors support requires the latest VoxCPM from GitHub:

```bash
pip install git+https://github.com/openbmb/VoxCPM.git
```

## Usage

```python
from voxcpm import VoxCPM
from huggingface_hub import snapshot_download
import soundfile as sf

# Download LoRA
lora_path = snapshot_download("aisyahsyihab/voxcpm-lora-indonesian-female-v2")

# Load model with LoRA
model = VoxCPM.from_pretrained(
    "openbmb/VoxCPM1.5",
    lora_weights_path=lora_path,
    load_denoiser=False
)

# Generate speech
audio = model.generate(
    text="Halo, apa kabar hari ini?",
    cfg_value=2.5,
    normalize=True
)

# Save output
sf.write("output.wav", audio, model.tts_model.sample_rate)
```

## Training Configuration

```yaml
lora:
  enable_lm: true
  enable_dit: true
  enable_proj: false
  r: 64
  alpha: 32
  dropout: 0.0
  target_modules_lm: ["q_proj", "v_proj", "k_proj", "o_proj"]
  target_modules_dit: ["q_proj", "v_proj", "k_proj", "o_proj"]

training:
  batch_size: 4
  grad_accum_steps: 4
  learning_rate: 0.0001
  warmup_steps: 100
  max_steps: 4000
```

## Hardware Requirements

- **Training:** NVIDIA RTX 5090 (32GB VRAM)
- **Inference:** ~6GB VRAM (with base model)

## Inference Tips

- **CFG value:** 2.0-3.0 (higher = more adherence to voice, lower = more natural)
- **Best for:** Casual Indonesian speech, conversational tone
- **Optimal text length:** 1-3 sentences at a time

## Changelog

- **v2 (2026-03-18):** Higher capacity LoRA (r=64), 400 samples, loss 0.750
- **v1 (2026-02-09):** Initial release, r=32, 112 samples, loss 0.790

## License

Apache 2.0 (following VoxCPM base model license)

## Acknowledgments

- [OpenBMB](https://github.com/OpenBMB) for VoxCPM 1.5
- Training conducted with VoxCPM's official LoRA training pipeline