AIbase
Home

whisper-compression-server

Public

Optimized Whisper speech-to-text with advanced model compression (LZMA/ZSTD), local serving, and persistent browser caching. Achieves 69% size reduction with 4-bit quantization.

browser-cachecompressionindexeddblzmamachine-learningonnxquantizationspeech-to-textwhisperzstd
Creat：2025-10-02T05:34:54
Update：2025-10-02T05:35:41
0
Stars
0
Stars Increase

Related projects

Browser Use

Hot
ai-agents

Make websites accessible for AI agents

73433
1年前
+154today

Redis

Hot
cache

For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

72066
1年前
+60today

DeepSpeed

billion-parameters

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

40940
1年前
+29today

AndroidUtilCode

android

:fire: Android developers should collect the following utils(updating).

33683
1年前
+1today

Real ESRGAN

amine

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

33472
3年前
+29today

Filebrowser

Hot
file-browser

? Web File Browser

32356
1年前
+68today

Phantomjs

automation

Scriptable Headless Browser

29484
1年前
-2today

Nginx

content-cache

The official NGINX Open Source repository.

28776
2年前
+41today

YAPI

ansi

A Collection of useful Methods in Java

27739
3年前
-1today

ArchiveBox

archivebox

? Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...

25897
1年前
+35today