---
license: apache-2.0
language: lug
base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
tags:
- text-to-speech
- tts
- lug
- qwen3-tts
- sunbird
library_name: qwen-tts
datasets:
- Sunbird/tts
---

# patrickcmd/qwen3-tts-salt-lug-0001

Single-speaker lug finetune of `Qwen/Qwen3-TTS-12Hz-1.7B-Base` on the `salt_lug_0001` voice
from [Sunbird/tts](https://huggingface.co/datasets/Sunbird/tts).

## Training summary

- Base model: `Qwen/Qwen3-TTS-12Hz-1.7B-Base`
- Dataset: Sunbird/tts (config: `lug`), filtered to `speaker_id == salt_lug_0001`
- Splits used: train (n=2395), dev (n=50)
- Best dev loss: 6.1474 @ step 300
- Hardware: 1× RTX A6000 48GB
- MLflow run: https://mlflow.sunbird.ai/#/experiments/0/runs/105b811c785246a1be7de6c6cb67fcc4

## Usage

```python
import torch
import soundfile as sf
from qwen_tts import Qwen3TTSModel

tts = Qwen3TTSModel.from_pretrained(
    "patrickcmd/qwen3-tts-salt-lug-0001",
    device_map="cuda:0",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
)
wavs, sr = tts.generate_custom_voice(
    text="Oli otya?",
    speaker="salt_lug_0001",
)
sf.write("out.wav", wavs[0], sr)
```

## Limitations

- Single speaker only (`salt_lug_0001`); voice cloning to other speakers is not the goal of this finetune.
- Trained for 1 epoch on a small subset; expect quality to vary on out-of-distribution lug text.