Fateh (@AngularPK) header
Fateh (@AngularPK) profile picture

Available for hire as  iOS Developer | Passionate about things we can do with SwiftUI and AI | Previous at Mity, GenieAI and GameStudio9

San Francisco, CA
Joined December 2016
Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)Photo by Fateh (@AngularPK)
I am building Haitruck A truck dispatching and a Load Board iOS app, that gets you moving with a prompt or few taps. #swiftui #iosdev #shipaton
2
2
348
This voice is my phone model, and it's only 25% trained. A 126 MB on-device TTS model learning to talk (and express) from 400 h of expressive speech, trained on 2x NVIDIA V100S GPUs. Full model tonight.
1
1
1
59
Progress on tiny expressive TTS: QC kept 99.7 % of 240K clips (386 h). The 24-layer teacher finished 20K steps in 13 h on my two V100S GPUs. Now distilling it into a 6-layer, ~126 MB on-device model. Results tonight.
1
22
Training a tiny on-device voice model that can talk naturally like laugh, sigh and gasp. I had a big model generate 240 K lines of audio, filtered out the bad takes, and now teaching a 126 MB model to talk like it. Results in about a day
20
Distilled Dia-1.6B into a 126 MB on-device TTS. Speech came out clean (WER 0.005), but the pauses and chuckles sounded fake, and Dia's own takes did too. The dataset was the problem, not the training. Ran a bake-off of 3 datasets, Orpheus won, regenerated 414 h of data. Retraining now.
1
48
Who put iOS in curiosity?
23
llama.cpp turns 1.0.0 🥳
25
Hey there!
1
1
44
My AI Fundamentals Course is close to ready to go live. aifundamentals.dev I'd love to give a few of you early access, for free, to test it out. Reply & Repost if you're interested, invite goes out tomorrow!
60
49
5
68
11,522
for first 3 secs I thought it was a SpaceX launch
1
25
this is an evidence how you can create great marketing videos without putting your app on dance floor (all the colors and unnecessary animations)
1
48
How I went from Full Time Senior Product Engineer to an unemployed vibe coder, here are the steps: [Thread]
36
On your mac. No backend. No API bills. Fully offline. I built Rona for Mac with SwiftUI, a voice companion powered by Apple Intelligence and a 174.5 MB local TTS model. You talk. It talks back, in different tones, warm & sharp. Source code: github.com/Fatehkhann/rona-v…
3
1
5
118
Bad AI bot experience, create good AI bots please.
34
Open source/weight AI isn’t partisan.
102
74
16
827
46,049
The stack behind on-device voice personas: Trainer: Sesame CSM-1B by @sesame . It speaks every training line in context: persona voice → user turn → reply, so the delivery stays conversational. Trainee: Kyutai Pocket TTS, fine-tuning the 24-layer teacher, then distilling to 6 layers for iOS.
Building voice personas for a fun experimental iOS app that run fully on-device. No cloud, no audio leaving the phone. Blended voices, conversational style distilled from Sesame CSM into Pocket TTS. Fine-tuning now. Results soon!
63
Building voice personas for a fun experimental iOS app that run fully on-device. No cloud, no audio leaving the phone. Blended voices, conversational style distilled from Sesame CSM into Pocket TTS. Fine-tuning now. Results soon!
1
117
Not a bad “first attempt”
38
You must respect Elon Musk because he’s changing your life
23