New version of livestream_video.sh - command line linux bash script that plays a livestream with AI transcription and support for multi-instance and multi-user

[antor44]

livestream_video.sh is a linux script to transcribe video livestream by feeding ffmpeg output to whisper.cpp at regular intervals, based on livestream.sh from whisper.cpp:

https://github.com/antor44/livestream_video

Author: Antonio R. Version: 1.60 License: GPL 3.0

This Linux script adds some new features:

-Support for IPTV, YouTube and Twitch

-Support for multi-instance and multi-user execution (For SMPlayer: Go to Preferences -> Interface -> Instances, and turn off the option to use only one instance)

-Language command-line option "auto" (for autodetection), "en", "es", "fr", "de", "he", "ar", etc., and "translate" for translation to English

-Quantized models support

-MacOS support.

Usage: ./livestream_video.sh stream_url [step_s] [model] [language] [translate] [quality] [ [player executable + player options] ]

Example (defaults if no options are specified):

./livestream_video.sh https://cbsnews.akamaized.net/hls/live/2020607/cbsnlineup_8/master.m3u8 4 base auto raw [smplayer]
Quality: The valid options are "raw," "upper," and "lower". "Raw" is used to download another video stream without any modifications for the player. "Upper" and "lower" download only one stream, which might correspond to the best or worst stream quality, re-encoded for the player.

"[player executable + player options]", valid players: smplayer, mpv, mplayer, vlc, etc... "[none]" or "[true]" for no player.

Step: Size of the parts into which videos are divided for inference, size in seconds.

Whisper models: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large

... with suffixes each too: -q4_0, -q4_1, -q4_2, -q5_0, -q5_1, -q8_0

Whisper languages (not all already fully supported):

auto (Autodetect), af (Afrikaans), am (Amharic), ar (Arabic), as (Assamese), az (Azerbaijani), be (Belarusian), bg (Bulgarian), bn (Bengali), br (Breton), bs (Bosnian), ca (Catalan), cs (Czech), cy (Welsh), da (Danish), de (German), el (Greek), en (English), eo (Esperanto), es (Spanish), et (Estonian), eu (Basque), fa (Persian), fi (Finnish), fo (Faroese), fr (French), ga (Irish), gl (Galician), gu (Gujarati), ha (Bantu), haw (Hawaiian), he ([Hebrew]), hi (Hindi), hr (Croatian), ht (Haitian Creole), hu (Hungarian), hy (Armenian), id (Indonesian), is (Icelandic), it (Italian), iw (Hebrew), ja (Japanese), jw (Javanese), ka (Georgian), kk (Kazakh), km (Khmer), kn (Kannada), ko (Korean), ku (Kurdish), ky (Kyrgyz), la (Latin), lb (Luxembourgish), lo (Lao), lt (Lithuanian), lv (Latvian), mg (Malagasy), mi (Maori), mk (Macedonian), ml (Malayalam), mn (Mongolian), mr (Marathi), ms (Malay), mt (Maltese), my (Myanmar), ne (Nepali), nl (Dutch), nn (Nynorsk), no (Norwegian), oc (Occitan), or (Oriya), pa (Punjabi), pl (Polish), ps (Pashto), pt (Portuguese), ro (Romanian), ru (Russian), sd (Sindhi), sh (Serbo-Croatian), si (Sinhala), sk (Slovak), sl (Slovenian), sn (Shona), so (Somali), sq (Albanian), sr (Serbian), su (Sundanese), sv (Swedish), sw (Swahili), ta (Tamil), te (Telugu), tg (Tajik), th (Thai), tl (Tagalog), tr (Turkish), tt (Tatar), ug (Uighur), uk (Ukrainian), ur (Urdu), uz (Uzbek), vi (Vietnamese), vo (Volapuk), wa (Walloon), xh (Xhosa), yi (Yiddish), yo (Yoruba), zh (Chinese), zu (Zulu)

translate: The "translate" option provides automatic English translation (only English is available).

The majority of online video streams should work.

Recommended Linux video player: SMPlayer based on mvp, or any other video player based on mpv, due to its capabilities to timeshift online streams for synchronized live video with the transcription.