Skip to content

Update requirements.txt instructions in example.md #425

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ella-granger wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

Update requirements.txt instructions in example.md #425

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
333aa72
Update requirements.txt instructions in example.md
ella-granger May 15, 2026
6660b46
Python version constraint
ella-granger May 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions website/content/pyharp_docs/example.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,16 +4,16 @@ To get the hang of building PyHARP applications, we'll deploy a state-of-the-art

### TIGER: a Powerful and Lightweight Speech Separation Model

DAW users such as video editors and podcasters often work with noisy speech recordings captured in less-than-ideal conditions, and "cleaning up" these recordings can be difficult and time-intensive. Luckily, there are a number of cutting-edge deep learning models capable of automating this clean-up process by separating a speech signal from any background sounds in a recording, including environment noise and even other speakers. In this tutorial, we'll look at [TIGER](https://arxiv.org/abs/2410.01469), a lightweight speech separation model capable of running efficiently on a laptop CPU. This means that you won't need a GPU for this tutorial -- just working HARP and PyHARP installations!
DAW users such as video editors and podcasters often work with noisy speech recordings captured in less-than-ideal conditions, and "cleaning up" these recordings can be difficult and time-intensive. Luckily, there are a number of cutting-edge deep learning models capable of automating this cleanup process by separating a speech signal from any background sounds in a recording, including environment noise and even other speakers. In this tutorial, we'll look at [TIGER](https://arxiv.org/abs/2410.01469), a lightweight speech separation model capable of running efficiently on a laptop CPU. This means that you won't need a GPU for this tutorial -- just working HARP and PyHARP installations!

To get started, we'll install [the code](https://github.com/JusperLee/TIGER) needed to run TIGER:
To get started, please set the Python version to `>=3.10, <=3.12` and install PyHARP. Then, we'll install [the code](https://github.com/JusperLee/TIGER) needed to run TIGER:

```
git clone https://github.com/JusperLee/TIGER.git
cd TIGER
```

In the `requirements.txt`, remove `triton==3.1.0` to avoid dependency issues. Then pip install:
In the `requirements.txt`, remove `triton==3.1.0` and add `typer==0.16.1` to avoid dependency issues. Then pip install:

```
pip install -r requirements.txt
Expand Down Expand Up @@ -222,4 +222,4 @@ Your terminal should display something like this:
This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)
```

Copy the public URL and open up HARP. Paste the URL as a `custom path...`, click `Load`, and voila -- you should now be able to run state-of-the-art speech separation in your DAW!
Copy the public URL and open up HARP. Paste the URL as a `custom path...`, click `Load`, and voila -- you should now be able to run state-of-the-art speech separation in your DAW!
Loading