or install with uv

uv pip install git+https://github.com/huggingface/transformers.git

Run `hf.py`. The file is as below.

```python
from transformers import AutoProcessor, DiaForConditionalGeneration


torch_device = "cuda"
model_checkpoint = "nari-labs/Dia-1.6B-0626"

text = [
    "[S1] Dia is an open weights text to dialogue model. [S2] You get full control over scripts and voices. [S1] Wow. Amazing. (laughs) [S2] Try it now on Git hub or Hugging Face."
]
processor = AutoProcessor.from_pretrained(model_checkpoint)
inputs = processor(text=text, padding=True, return_tensors="pt").to(torch_device)

model = DiaForConditionalGeneration.from_pretrained(model_checkpoint).to(torch_device)
outputs = model.generate(
    **inputs, max_new_tokens=3072, guidance_scale=3.0, temperature=1.8, top_p=0.90, top_k=45
)

outputs = processor.batch_decode(outputs)
processor.save_audio(outputs, "example.mp3")

Install dia

pip install -e .

Or you can install without cloning.

```bash

---

# Install directly from GitHub
pip install git+https://github.com/nari-labs/dia.git

Now, run some examples.

python example/simple.py

---

## 💻 Hardware and Inference Speed

Dia has been tested on only GPUs (pytorch 2.0+, CUDA 12.6). CPU support is to be added soon.
The initial run will take longer as the Descript Audio Codec also needs to be downloaded.

These are the speed we benchmarked in RTX 4090.

| precision | realtime factor w/ compile | realtime factor w/o compile | VRAM |
|:-:|:-:|:-:|:-:|
| `bfloat16` | x2.1 | x1.5 | ~4.4GB |
| `float16` | x2.2 | x1.3 | ~4.4GB |
| `float32` | x1 | x0.9 | ~7.9GB |

We will be adding a quantized version in the future.

If you don't have hardware available or if you want to play with bigger versions of our models, join the waitlist [here](https://tally.so/r/meokbo).

---

## 🪪 License

This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.