Alpay Calalli

iOS developer, one of the WWDC SSC winners in 2024 and 2025. Interested in Machine Learning and Computer Vision.

[Alpay Calalli @calalli24]

I've open-sourced the project, feel free to check it out and share any feedback.

https://t.co/2YQHCTGxeL

[Alpay Calalli @calalli24]

Here is a demo video of my submission this year for the Swift Student Challenge.

It is a basketball analyzer app, that counts your shots, calculates metrics like Release Angle, Ball Speed, Miss Reason(ex. : Short, Long).

#swiftstudentchallenge

[Alpay Calalli @calalli24]

@radiofun8 I guess you use CoreML converted version of sam3, can you share the model source?

[Alpay Calalli @calalli24]

@ollmannphilipp Congrats! Would love to see your submission

[Prince Canuma @Prince_Canuma]

Day 1 of 3 days of MLX:

Introducing MLX-Audio-Swift SDK 🚀

A modular Swift SDK for voice agents and tasks on Apple Silicon built by @lllucas and yours truly.

iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence:

🗣️ Text-to-Speech (TTS)
👂 Speech-to-Text (STT)
🔄 Speech-to-Speech (STS)
🎙️ Voice Activity Detection (VAD) and more.

Only import the capabilities you need, nothing extra.

Get started today and leave us a star ⭐️

https://t.co/AXJvHw0DY6

[Alpay Calalli @calalli24]

@Prince_Canuma 🤔

[Alpay Calalli @calalli24]

@ronuhz *using old SFSpeechRecognizer

[Alpay Calalli @calalli24]

@ronuhz probably making app work on iOS 18 with availability flags, and notifying reviewers about this issue in the submission form.

[Alpay Calalli @calalli24]

Inspired by⬇️ Will try to implement most of the stuff in that project on a macOS/iOS project.
https://t.co/uCClrEMVxa

[SkalskiP @skalskip92]

this might be the coolest blogpost I ever written

I dove deep into:

- player detection with RF-DETR
- player tracking with SAM2
- team clustering with SigLIP and K-means
- number recognition with SmolVLM2 and ResNet

I hope you'll like it

link: https://t.co/PPPGTD8L2v

[Alpay Calalli @calalli24]

Switched to the YOLO11 model by Roboflow. The result is a lot more accurate and much less flickery.

In the video, you can also see a comparison between two models trained on the same dataset:
-One trained in Create ML using a YOLOv2-based architecture
-A YOLO11 model by Roboflow

[Alpay Calalli @calalli24]

Swift / macOS project for detecting and tracking the ball, players, and other on-court elements in a basketball game.

I trained a custom CoreML model, running fully on-device. Accuracy isn’t perfect yet, so I’ll keep improving it.

[Alpay Calalli @calalli24]

Dataset: basketball-player-detection-3 (CC BY 4.0)
Link: https://t.co/9TC9sQBHhQ

[Alpay Calalli @calalli24]

@Droni0s Me too. Still not sure about whether my project having no "story" will have a negative effect on the judgement process or not. Had the same concern last year, since app was requiring you to upload a video or use my demo one to use the app.

[Alpay Calalli @calalli24]

Project template and tracking algorithm are from "Human Traffic Analyzer" article by @itsuki68391179.
https://t.co/SeI9ueXsvX

[Alpay Calalli @calalli24]

Swift / macOS project for detecting and tracking the ball, players, and other on-court elements in a basketball game.

I trained a custom CoreML model, running fully on-device. Accuracy isn’t perfect yet, so I’ll keep improving it.

[Chad Etzel @jazzychad]

🧞‍♂️and here it is!! a pure SwiftUI + Metal implementation of the legendary OSX genie effect 🔥

[Alpay Calalli @calalli24]

@itsuki68391179 @gitconnected Maybe this is intentional for CentroidTracker, but still I think there should be some ways to avoid relying on results of object detection model on every frame.

[Alpay Calalli @calalli24]

@itsuki68391179 @gitconnected For example, to use this on a video, CentroidTracker requires you to run object detection on every frame, (which is, I guess not the case for TrackObjectRequest), so if detection fails on a certain frame, bounding box disappears. What might be the possible solutions for this?

[Alpay Calalli @calalli24]

@jazzychad Your last thread was really nice

[Alpay Calalli @calalli24]

@sach1n @fluidaudio @liquidai @Apple Using FluidAudio, my diarization result is so inaccurate. But saw your demo, so it works fine I guess.
Can you share your function that handles the diarization?

[Marcin Krzyzanowski @krzyzanowskim]

please somebody start sharing interesting things again