README.md

metadata

title: Diffusion Speech 360h
emoji: 🏆
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 5.9.1
python_version: 3.11
app_file: app.py
pinned: false
license: mit
models:
  - ntt123/diffusion-speech-360h
preload_from_hub: >-
  true - ntt123/diffusion-speech-360h
  acoustic_model_0140000.pt,duration_model_0120000.pt
short_description: A simple diffusion-based text to speech model

uv run synthesize.py \
--duration-model-config ./train_duration_dit_s.yaml \
--acoustic-model-config ./train_acoustic_dit_b.yaml \
--duration-model-checkpoint ./duration_model_0120000.pt \
--acoustic-model-checkpoint ./acoustic_model_0140000.pt \
--speaker-id 1914 \
--output-file ./audio.wav \
--text "Ilya has made several major contributions to the field of deep learning."