diff --git a/docs/assets/80s-pop.wav b/docs/assets/80s-pop.wav new file mode 100644 index 00000000..30606cb7 Binary files /dev/null and b/docs/assets/80s-pop.wav differ diff --git a/docs/assets/subway.wav b/docs/assets/subway.wav new file mode 100644 index 00000000..da94b852 Binary files /dev/null and b/docs/assets/subway.wav differ diff --git a/docs/images/audiocraft_jupyterlab_demo.png b/docs/images/audiocraft_jupyterlab_demo.png new file mode 100644 index 00000000..a585641b Binary files /dev/null and b/docs/images/audiocraft_jupyterlab_demo.png differ diff --git a/docs/tutorial_audiocraft.md b/docs/tutorial_audiocraft.md new file mode 100644 index 00000000..2fe6c741 --- /dev/null +++ b/docs/tutorial_audiocraft.md @@ -0,0 +1,87 @@ +# Tutorial - AudioCraft + +Let's run Meta's [AudioCraft](https://github.com/facebookresearch/audiocraft), to produce high-quality audio and music on Jetson! + +!!! abstract "What you need" + + 1. One of the following Jetson: + + Jetson AGX Orin 64GB + Jetson AGX Orin (32GB) + Jetson Orin Nano Orin (8GB) + + 2. Running one of the following [JetPack.5x](https://developer.nvidia.com/embedded/jetpack) + + JetPack 5.1.2 (L4T r35.4.1) + JetPack 5.1.1 (L4T r35.3.1) + JetPack 5.1 (L4T r35.2.1) + + 3. Sufficient storage space (preferably with NVMe SSD). + + - `10.7 GB` for `audiocraft` container image + - Space for checkpoints + +## Clone and set up `jetson-containers` + +``` +git clone https://github.com/dusty-nv/jetson-containers +cd jetson-containers +sudo apt update; sudo apt install -y python3-pip +pip3 install -r requirements.txt +``` +## How to start + +Use `run.sh` and `autotag` script to automatically pull or build a compatible container image. + +``` +cd jetson-containers +./run.sh $(./autotag audiocraft) +``` + +The container has a default run command (`CMD`) that will automatically start the Jupyter Lab server. + +Open your browser and access `http://:8888`. + +> The default password for Jupyter Lab is `nvidia`. + +## Run Jupyter notebooks + +AudioCraft repo comes with demo Jupyter notebooks. + +On Jupyter Lab navigation pane on the left, double-click `demos` folder. + +![](./images/audiocraft_jupyterlab_demo.png) + +### AudioGen demo + +For "**Text-conditional Generation**", you should get something like this. + + + +!!! info + + You may encounter an error message like the following when executing the first cell, but you can keep going. + ``` + A matching Triton is not available, some optimizations will not be enabled. + Error caught was: No module named 'triton' + ``` + +!!! warning + + When running the 5-th cell of `audiogen_demo.ipynb`, you may run into "**Failed to load audio**" RuntimeError. + +### MusicGen demo + +For "**Text-conditional Generation**", you should get something like this. + + + +!!! warning + + When running the 5-th cell of `musicgen_demo.ipynb`, you may run into "**Failed to load audio**" RuntimeError. \ No newline at end of file diff --git a/mkdocs.yml b/mkdocs.yml index 7f3cceb6..a49b9bbf 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -87,6 +87,8 @@ nav: # - NanoOWL: tutorial_nanoowl.md - Vector Database: - NanoDB: tutorial_nanodb.md + - Audio: + - Audiocraft: tutorial_audiocraft.md # - Tools: # - LangChain: tutorial_distillation.md - Tips: