OpenVINO & Linux

minyves · March 8, 2024, 3:10pm

I compiled Audacity with OpenVINO on Ubuntu 22.04 following this readme:

intel/openvino-plugins-ai-audacity/blob/main/doc/build_doc/linux/README.md

# Audacity OpenVINO module build for Linux (Ubuntu 22.04)

Hi! The following is the process that we use when building the Audacity modules for Linux. These instructions are for Ubuntu 22.04, so you may need to adapt them slightly for other Linux distros.

## High-Level Overview
Before I get into the specifics, at a high-level we will be doing the following:
* Cloning & building whisper.cpp with OpenVINO support (For transcription audacity module)
* Cloning & building openvino-stable-diffusion-cpp (This is to support Music Generation & Remix features)
* Cloning & building Audacity without modifications (just to make sure 'vanilla' build works fine)
* Adding our OpenVINO module src's to the Audacity source tree, and re-building it.

## Dependencies
Here are some of the dependencies that you need to grab. If applicable, I'll also give the cmd's to set up your environment here.
* Build Essentials (GCC & CMake)
```
sudo apt install build-essential
```
* OpenVINO - Download appropriate version from [here](https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/linux/). For these instructions, we will use ```l_openvino_toolkit_ubuntu22_*x86_64tgz```.
```
# Extract it

This file has been truncated. show original

Everything seemed to be alright, but I get an error when I want to use it:

15:43:40: Error: In Noise Suppression Compilation, exception: Exception from src/inference/src/core.cpp:85:
Exception from src/inference/src/model_reader.cpp:137:
Unable to read the model: /usr/local/lib/openvino-models/noise-suppression-denseunet-ll-0001.xml

Following the readme no noise-suppression-denseunet-ll-0001.xml has been generated, and I can’t select anything else from within audacity (from effect/openvino ai effect/openvino noise suppression).

What am I missing?

I also found this question:

OpenVINO build for Ubuntu 22.04

and could have answered it, if this forum wouldn’t automatically close topics after 30 days (what seems ridiculously short)
My answer is: the whole thing (git-clones, audacity, openvino and openvino-models etc) is 11.2 GB

Ryguy · March 8, 2024, 5:35pm

Hi @minyves,

Ah, okay. Sorry about that… we’ve been refactoring that README with the instructions to pull models directly from hugging face, and elsewhere (like open model zoo in this case). Let me update the README that shows how/where to grab noise-suppression-denseunet-ll-0001.xml.

I’ll update this topic when I’ve updated the README, but in the meantime you can grab the two required files (the .xml / .bin) from here:
https://storage.openvinotoolkit.org/repositories/open_model_zoo/2023.0/models_bin/1/noise-suppression-denseunet-ll-0001/FP16/

Download those, and drop them into the openvino-models folder.

As a side note, I’m currently working on integrating better quality & faster models (deepfilternet2 & deepfilternet3) into the project… should be merged next few days, so stay tuned.

system · April 7, 2024, 3:10pm

This topic was automatically closed after 30 days. New replies are no longer allowed.