doing something

Okay, I've made a working colab with these speeding mechanisms for Whisper:

- HQQ (quantize linear layers to 4-bit)
- torch.compile
- use static cache

Colab:

https://colab.research.google.com/drive/1zERp53F7gmE58OiqFR0iNV3gw3ybiwHM?usp=sharing

RTF: 0.0531 (batch size = 1) with large-v3

#ai #whisper #asr

Google

Nightly torch with HQQ (nbits=4) + torch.compile + static cache + Whisper.ipynb

Colab notebook

678 viewsedited 10:47

doing something

Forwarded from Feed-Master

Why Rust?

rerun.io

Why Rust?

I've been a programmer for 20+ years, and few things excite me as much as Rust. My background is mostly in C++, though I have also worked in Python and Lua, and dabbled in many more languages. I started writing Rust around 2014, and since 2018 I've been writing…

87 views19:58

doing something

bs=24, whisper large-v3

https://github.com/egorsmkv/optimized-whisper

#ai #asr

238 viewsedited 11:22

doing something

bs=24, whisper large-v3 https://github.com/egorsmkv/optimized-whisper #ai #asr

A test, total time of the video: 1:51:45 (link)

Stats:

- Duration: 6480.020 seconds
- RTF: 0.0153
- Elapsed: 98.9704 seconds

Hardware:

- GPU: RTX 4000 Ada

#ai #asr

538 viewsedited 11:29

doing something

A test, total time of the video: 1:51:45 (link) Stats: - Duration: 6480.020 seconds - RTF: 0.0153 - Elapsed: 98.9704 seconds Hardware: - GPU: RTX 4000 Ada #ai #asr

arestovich_ukrainian.txt

153.5 KB

517 views11:33

doing something

https://github.com/mitsuhiko/minijinja

#rust

GitHub

GitHub - mitsuhiko/minijinja: MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2

MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2 - mitsuhiko/minijinja

96 views14:10

doing something

Nice services:

- https://github.com/huridocs/pdf-document-layout-analysis

- https://github.com/huridocs/pdf-table-of-contents-extractor

- https://github.com/huridocs/pdf-text-extraction

#docker #ai #nlp #pdf #opensource

483 viewsedited 14:27

doing something

Use it for good:

https://github.com/egorsmkv/vad-chunk-size

#ai #asr #vad

GitHub

GitHub - egorsmkv/vad-chunk-size: Extracted chunk-size VAD from WhisperX

Extracted chunk-size VAD from WhisperX. Contribute to egorsmkv/vad-chunk-size development by creating an account on GitHub.

91 views17:39

doing something

Forwarded from Feed-Master

Burn 0.14.0 Released: The First Rust-Native Deep Learning Framework

burn.dev

Burn 0.14.0 Release Notes

This release marks the debut of our CubeCL integration, which brings cross-platform GPU programming capabilities directly to Rust.
As always, it also includes numerous bug fixes, performance enhancements, new tensor operations, and improved documentation.

92 views18:44

doing something

https://github.com/esimov/pigo supports WASM

#go #cv #wasm

274 viewsedited 20:39

doing something

Forwarded from Feed-Master

Rspack 1.0 – the next generation JavaScript bundler written in Rust

rspack.rs

Announcing Rspack 1.0 - Rspack

Today Rspack has reached a new milestone - 1.0. This means that Rspack is production-ready, covers most of webpack's APIs and features, and is now prepared to support more users.

89 views06:23

doing something

Feed-Master

Rspack 1.0 – the next generation JavaScript bundler written in Rust

Looks like an alternative to https://github.com/vitejs/vite or https://github.com/farm-fe/farm

92 viewsedited 06:23

doing something

https://github.com/xlab/c-for-go

#go

GitHub

GitHub - xlab/c-for-go: Automatic C-Go Bindings Generator for Go Programming Language

Automatic C-Go Bindings Generator for Go Programming Language - xlab/c-for-go

90 views12:05

doing something

Fast denoiser based on diffusions:

https://github.com/sp-uhh/sgmse_crp

RTF about 0.0375 on RTX 4k Ada, because it needs only 1 reverse step

#ai #diffusions #speech

GitHub

GitHub - sp-uhh/sgmse_crp

Contribute to sp-uhh/sgmse_crp development by creating an account on GitHub.

97 viewsedited 15:23

doing something

Forwarded from Feed-Master

Robyn – A super fast Python web framework written in Rust

GitHub

GitHub - sparckles/Robyn: Robyn is a Super Fast Async Python Web Framework with a Rust runtime.

Robyn is a Super Fast Async Python Web Framework with a Rust runtime. - sparckles/Robyn

114 views21:58

doing something

We’ve been talking about PDF processing yesterday at UDS and today I’ve discovered it:

https://x.com/hu_yifei/status/1828870309857915341?s=46&t=7jwH29MvU0R301CgvqVBYw

#cv #ai

351 views05:46

doing something

This author has another model (based on Florence-2) that extracts parts in the article: https://huggingface.co/yifeihu/TFT-ID-1.0

In the album some examples how it works. Next we can OCR these images and analyse using other LLMs.

#ai #cv

332 views07:12

About

Blog

Apps

Platform