spencer
28012e70e0
- Implemented `storage.py` for managing metadata storage, including sample addition, retrieval, and review state management. - Created `training.py` for training a local model using Random Forest, including functions for training and predicting samples. - Developed a web interface in `app.js` for capturing audio samples, managing labels, and training the model. - Added HTML structure in `index.html` for the SnoreStopper control room with sections for sample capture, overnight gathering, training, and status display. - Styled the application with `styles.css` to enhance user experience and interface aesthetics.
13 lines
1020 B
Markdown
13 lines
1020 B
Markdown
I want to build an app based on Python and a web UI
|
|
|
|
The project goal is to build an all in one solution for tracking snooring and tracking sleep.
|
|
|
|
to do this we need to allow the end user to
|
|
- select an audio input device from the ones connected to the 'server'
|
|
- to record ambiant room noise and gather samples of snoring
|
|
- to do this we'll need to define good sample sizes and periods of recording
|
|
- we'll also need to save the files in a audio format that doesn't pin the CPU/gpu but also doesn't waste filesize pointessly.
|
|
- We will likely also want to store the produced data from the sample that will be used by the network for training (i am thinking a basic spectrogram stored as a png)
|
|
- User will record samples over a couple nights, find examples of snoring, train the AI, let it try flagging the snoring events itself and once it's done trigger the anti-snoring events
|
|
- must be self-hosted and self-trained, designed to be safe and appless so people are comfortable with passive recording
|