Loading video...

Video Failed to Load

Go Home

Introducing WhisperKit

argmax's profile picture

argmax

4,497 subscribers

98,394 views • 2 years ago •via X (Twitter)

Health & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

10 Comments

batuhan the fal guy's profile picture
batuhan the fal guy2 years ago

looks 🔥

murat 🍥's profile picture
murat 🍥2 years ago

how is this different from whisper.cpp's metal/coreml implementation?

Miguel Piedrafita ✨'s profile picture
Miguel Piedrafita ✨2 years ago

oooo this is really cool!

Alexandre Berriche's profile picture
Alexandre Berriche2 years ago

Super cool !

BLENDER SUSHI 🫶 X - 24/7 Blenderian's profile picture
BLENDER SUSHI 🫶 X - 24/7 Blenderian2 years ago

I tried it so far I like the realtime streaming and translation. I test it while YouTube running on TV and translation works 50-60% some times it's buffering. Can it tend later audio from say running audio app like YouTube or Twitter video?

Tomas Maixner | Neuralbyte's profile picture
Tomas Maixner | Neuralbyte2 years ago

I have problems without loading

Anton Panasenko's profile picture
Anton Panasenko2 years ago

Any plan for diarization?

argmax's profile picture
argmax2 years ago

Yes

Mark Lord's profile picture
Mark Lord1 year ago

Hi! 👋 Quick qu; is my understanding right that WhisperKit processes live audio in chunks and stitches the transcript together? Or does it keep a run-on KV cache of encoded audio which grows as more audio is streamed in + encoded?

Tony Raha's profile picture
Tony Raha2 years ago

@osanseviero This is so cool! Can you please add an action in iOS shortcuts app so we can integrate it with other iOS native apps?

Related Videos

Introducing Real-time Transcription with Speakers! - Step change in accuracy, surpassing top cloud APIs - Faster than real-time on Mac and iPhone - Still under 3 watts when all features are enabled Available in Argmax SDK 2.0 for early access! Benchmarks and details in comments.
1:01

Introducing Real-time Transcription with Speakers! - Step change in accuracy, surpassing top cloud APIs - Faster than real-time on Mac and iPhone - Still under 3 watts when all features are enabled Available in Argmax SDK 2.0 for early access! Benchmarks and details in comments.

argmax

72,819 views • 5 months ago

Introducing Real-time Transcription with Nvidia Parakeet - Same top accuracy as file transcription - Best-in-market 160 ms lips-to-screen latency - 744x more cost-efficient compared to cloud APIs - Available in Argmax Pro SDK starting today! Link in comments
0:41

Introducing Real-time Transcription with Nvidia Parakeet - Same top accuracy as file transcription - Best-in-market 160 ms lips-to-screen latency - 744x more cost-efficient compared to cloud APIs - Available in Argmax Pro SDK starting today! Link in comments

argmax

58,986 views • 10 months ago

Introducing Argmax Local Server Run our state-of-the-art real-time transcription server directly on Mac! 0:31 Feature complete for AI Meeting Notes apps 0:49 Migrate from cloud APIs with 1 line of code 1:05 Fastest speech models with top accuracy 1:31 Other apps do not slow down Available starting today with Python, JavaScript, and Rust clients! Details in comments
2:19

Introducing Argmax Local Server Run our state-of-the-art real-time transcription server directly on Mac! 0:31 Feature complete for AI Meeting Notes apps 0:49 Migrate from cloud APIs with 1 line of code 1:05 Fastest speech models with top accuracy 1:31 Other apps do not slow down Available starting today with Python, JavaScript, and Rust clients! Details in comments

argmax

13,003 views • 10 months ago

TTSKit now achieves sub-100ms time-to-first-byte for Qwen3-TTS 1.7b on Apple Silicon! Link to the code repo and details in comments.
0:28

TTSKit now achieves sub-100ms time-to-first-byte for Qwen3-TTS 1.7b on Apple Silicon! Link to the code repo and details in comments.

argmax

30,154 views • 3 months ago

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)
0:20

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)

argmax

73,996 views • 2 years ago

Real-time Transcription with Speakers is now generally available on iOS and macOS! Details for installing or simply testing Argmax SDK 2 are in the comments.
0:51

Real-time Transcription with Speakers is now generally available on iOS and macOS! Details for installing or simply testing Argmax SDK 2 are in the comments.

argmax

29,142 views • 3 months ago

Argmax now runs on Google Tensor TPU, the first-ever SDK to harness this edge inference accelerator! Tensor TPU enabled us to deploy billion-scale transformers reliably on Pixel phones without impacting battery life or resource contention with traditional workloads.
0:26

Argmax now runs on Google Tensor TPU, the first-ever SDK to harness this edge inference accelerator! Tensor TPU enabled us to deploy billion-scale transformers reliably on Pixel phones without impacting battery life or resource contention with traditional workloads.

argmax

26,957 views • 1 month ago

WhisperKit Benchmarks are live on Hugging Face! Speech-to-text systems are hard to benchmark holistically given trade-offs across latency, memory, energy efficiency and accuracy. On-device testing makes it doubly challenging. Here is our first version built with Gradio 🧵
0:32

WhisperKit Benchmarks are live on Hugging Face! Speech-to-text systems are hard to benchmark holistically given trade-offs across latency, memory, energy efficiency and accuracy. On-device testing makes it doubly challenging. Here is our first version built with Gradio 🧵

argmax

13,757 views • 1 year ago

WhisperKit x OpenAI Whisper Large v3 Turbo Released a few hours ago, this model is 8x faster than the original Large v3 model while retaining its high-quality multilingual capabilities. Here is a demo using our test app. Test app: GitHub (MIT): OpenAI release:
0:44

WhisperKit x OpenAI Whisper Large v3 Turbo Released a few hours ago, this model is 8x faster than the original Large v3 model while retaining its high-quality multilingual capabilities. Here is a demo using our test app. Test app: GitHub (MIT): OpenAI release:

argmax

47,779 views • 1 year ago

Introducing a game changer in home health: Introducing U-Scan. #CES2023
0:46

Introducing a game changer in home health: Introducing U-Scan. #CES2023

Withings

161,079 views • 3 years ago

Introducing
1:19

Introducing

SIP

344,961 views • 1 year ago

Introducing.
0:25

Sensitive content

Introducing.

Useless Utility

70,007 views • 2 years ago

Introducing...
0:25

Introducing...

cto.new

1,491,054 views • 8 months ago

Introducing #AZAPAC!
4:04

Introducing #AZAPAC!

AZAPAC

1,748,946 views • 6 months ago

Introducing V2.
5:08

Introducing V2.

FrameAuth (formerly FramerAuth)

10,600 views • 10 days ago

Introducing Union.
1:18

Introducing Union.

Union

84,246 views • 9 months ago

Introducing: Trailblaze.
0:40

Introducing: Trailblaze.

Trailblaze

328,239 views • 2 years ago

Introducing VIGGZ
2:49

Introducing VIGGZ

eRa

13,444 views • 2 months ago

finally introducing…
1:47

finally introducing…

acervo loona

129,291 views • 6 months ago

Introducing: Coven
1:02

Introducing: Coven

Women of Halo ✨

44,468 views • 1 year ago