README.md

---
language:
  - dv
license: other
license_name: coqui-public-model-license
license_link: https://coqui.ai/cpml
tags:
  - text-to-speech
  - tts
  - voice-cloning
  - xtts
  - dhivehi
  - thaana
  - maldives
library_name: coqui
pipeline_tag: text-to-speech
base_model: coqui/XTTS-v2
---

# XTTS v2 - Dhivehi (Thaana)

Fine-tuned [XTTS v2.0](https://huggingface.co/coqui/XTTS-v2) for **Dhivehi** (Maldivian, Thaana script) text-to-speech with zero-shot voice cloning.

## Model Details

- **Base model:** XTTS v2.0 (Coqui)
- **Language:** Dhivehi (dv) - Thaana script
- **Architecture:** GPT-2 + DVAE + HiFiGAN vocoder
- **Audio:** 24kHz output
- **Training step:** 95366

## Training Data

~59,000 samples (~75+ hours) from multiple Dhivehi speech sources:
- [Serialtechlab/dhivehi-javaabu-speech-parquet](https://huggingface.co/datasets/Serialtechlab/dhivehi-javaabu-speech-parquet) - news/article narration
- [Serialtechlab/dv-presidential-speech](https://huggingface.co/datasets/Serialtechlab/dv-presidential-speech) - presidential addresses
- [Serialtechlab/dhivehi-tts-female-01](https://huggingface.co/datasets/Serialtechlab/dhivehi-tts-female-01) - female speaker
- [alakxender/dv-audio-syn-lg](https://huggingface.co/datasets/alakxender/dv-audio-syn-lg) - synthetic speech (subset)

## Usage

### Install

```bash
pip install coqui-tts
```

### Inference

```python
import torch, torchaudio
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts

# Download all files from this repo into a local directory

config = XttsConfig()
config.load_json("config.json")

model = Xtts.init_from_config(config)
model.load_checkpoint(
    config,
    checkpoint_path="model.pth",
    vocab_path="vocab.json",
    eval=True,
    strict=False,
)
model.cuda()

# Get speaker embedding from a reference WAV (5-15 sec of clean speech)
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(
    audio_path=["reference.wav"],
    gpt_cond_len=24,
    gpt_cond_chunk_len=4,
)

# Generate speech
out = model.inference(
    text="\u0784\u07a8\u0790\u07b0\u0789\u07a8\ufdf2 \u0783\u07a6\u0781\u07aa\u0789\u07a7\u0782\u07a8 \u0783\u07a6\u0781\u07a9\u0789\u07a8",
    language="dv",
    gpt_cond_latent=gpt_cond_latent,
    speaker_embedding=speaker_embedding,
    temperature=0.7,
)

wav = torch.tensor(out["wav"]).unsqueeze(0)
torchaudio.save("output.wav", wav, 24000)
```

## Files

- `model.pth` - Fine-tuned GPT checkpoint
- `config.json` - Model configuration
- `vocab.json` - Extended BPE vocabulary (base XTTS + Thaana characters)
- `dvae.pth` - Discrete VAE (from base XTTS v2.0)
- `mel_stats.pth` - Mel spectrogram normalization stats (from base XTTS v2.0)

## Limitations

- Voice cloning quality depends on the reference audio (clean, 5-15 seconds recommended)
- Text longer than ~300 characters may be truncated
- Some rare Dhivehi words may be mispronounced
- Model is still being actively trained - newer checkpoints may be uploaded

## License

This model inherits the [Coqui Public Model License](https://coqui.ai/cpml) from the base XTTS v2.0 model.