- Libraries
- LiteRT
How to use mlboydaisuke/Dia2-1B-LiteRT with LiteRT:
# No code snippets available yet for this library.
# To use this model, check the repository files and the library's documentation.
# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js
- Moshi
How to use mlboydaisuke/Dia2-1B-LiteRT with Moshi:
# pip install moshi
# Run the interactive web server
python -m moshi.server --hf-repo "mlboydaisuke/Dia2-1B-LiteRT"
# Then open https://localhost:8998 in your browser
# pip install moshi
import torch
from moshi.models import loaders
# Load checkpoint info from HuggingFace
checkpoint = loaders.CheckpointInfo.from_hf_repo("mlboydaisuke/Dia2-1B-LiteRT")
# Load the Mimi audio codec
mimi = checkpoint.get_mimi(device="cuda")
mimi.set_num_codebooks(8)
# Encode audio (24kHz, mono)
wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples]
with torch.no_grad():
codes = mimi.encode(wav.cuda())
decoded = mimi.decode(codes) - Dia2
How to use mlboydaisuke/Dia2-1B-LiteRT with Dia2:
from dia2 import Dia2, GenerationConfig, SamplingConfig
dia = Dia2.from_repo("mlboydaisuke/Dia2-1B-LiteRT", device="cuda", dtype="bfloat16")
config = GenerationConfig(
cfg_scale=2.0,
audio=SamplingConfig(temperature=0.8, top_k=50),
use_cuda_graph=True,
)
result = dia.generate("[S1] Hello Dia2!", config=config, output_wav="hello.wav", verbose=True)
- Notebooks
- Google Colab
- Kaggle
