Tootfinder

Opt-in global Mastodon full text search. Join the index!

@bici@mastodon.social
2024-04-21 21:58:00

Within the depths of Vancouver Island, where the mist-laden forests whisper secrets, resides Emma-Bethany May. She is a conjurer of steel dreams, and the guardian of wzrd. bikes.
#BIKES

@arXiv_csSD_bot@mastoxiv.page
2024-06-17 07:26:10

Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection
Haoyu Wang, Guoqiang Hu, Guodong Lin, Wei-Qiang Zhang, Jian Li
arxiv.org/abs/2406.10052

@fipmusicbot@mastodonapp.uk
2024-05-18 10:55:11

🔊 #NowPlaying on fip
Cecile Campbell:
🎵 Whisper to me
#CecileCampbell
open.spotify.com/track/5xgPgAW
studioone.bandcamp.com/track/w

@aral@mastodon.ar.al
2024-06-17 13:43:13

Oooh, ooh, ooh… look what just arrived! I’ve been waiting almost a year for it and boy was it worth the wait. My new Linux laptop is a… tablet? Yep. The StarLabs StarLite.
Oh and the screen on this thing! 😍
ie.starlabs.systems/pages/star

A box for a rectangular object that looks like a tablet.
Sideways view of box showing a wireframe in silver of the side of the tablet that’s in it with power and volume buttons showing, as well as a camera protruding from the bottom.
A rectangular object wrapped in a blue case with the StarLabs logo (a three point star with three additional, disjointed arms/points).
A white hand holding a tablet in portrait orientation with my web site (https://ar.al) on it. In the background is a desk, a stack of laptops, a leg wearing jeans, and a lego keyboard, partially visible.
@arXiv_eessAS_bot@mastoxiv.page
2024-06-17 07:01:37

Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
Andrew Rouditchenko, Yuan Gong, Samuel Thomas, Leonid Karlinsky, Hilde Kuehne, Rogerio Feris, James Glass
arxiv.org/abs/2406.10082

@arXiv_csCL_bot@mastoxiv.page
2024-05-06 08:26:37

This arxiv.org/abs/2402.08021 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCL_…

@freegames@mastodon.pnpde.social
2024-05-23 18:00:05

Spirits of Mystery: Whisper of the Past
gaming.amazon.com/spirits-of-m

@mikebabyak@musicians.today
2024-05-11 15:57:16

During his entire first year with us, our #rescue #chihuahua Linus was so shy you could count on one hand the number of times he barked; and when he did it was barely a whisper. We even wondered whether there was something wrong with his voice. But then my wife taught him “the supper dance” and now…

Long haired chihuahua running in circles around porch while woman encourages him.
@penguin42@mastodon.org.uk
2024-05-09 13:44:38

Now this is some good news! Gene therapy fixing deafness in a kid before they even really know about it;
#science

@BBC2MusicBot@mastodonapp.uk
2024-04-23 06:43:07

🔊 #NowPlaying on BBCRadio2's #TheZoeBallBreakfastShow
George Michael:
🎵 Careless Whisper
#GeorgeMichael
open.spotify.com/track/4jDmJ51
souljack.bandcamp.com/track/ge

@arXiv_eessAS_bot@mastoxiv.page
2024-06-17 07:01:30

Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition
Yicong Jiang, Tianzi Wang, Xurong Xie, Juan Liu, Wei Sun, Nan Yan, Hui Chen, Lan Wang, Xunying Liu, Feng Tian
arxiv.org/abs/2406.09873

@blakes7bot@botsin.space
2024-05-01 07:49:48

Series B, Episode 11 - Gambit
CEVEDIC: [Off-screen whisper] Docholli's in there somewhere, but he's not a problem. First we get Travis.
UN-NAMED HENCHMAN: Okay.
blake.torpidity.net/s/211/421 📺 B7B2

@paulomalley@c.im
2024-05-27 12:55:05

Tired of 😖 manual video transcription or relying on unreliable auto-captioning? Discover the power of Whisper Transcription for Mac! 💻
This innovative tool uses advanced AI to quickly and accurately transcribe your files and works completely offline, keeping your data secure. 🚀 And what's more, it's available to use completely for free!
Learn how to generate high-quality transcripts and subtitle files effortlessly in my latest video tutorial.
🎥

YouTube Thumbnail image featuring the Apple Logo with the caption "Free, Fast and Accurate Transcripts"
@arXiv_csSD_bot@mastoxiv.page
2024-05-07 07:35:24

Whispy: Adapting STT Whisper Models to Real-Time Environments
Antonio Bevilacqua, Paolo Saviano, Alessandro Amirante, Simon Pietro Romano
arxiv.org/abs/2405.03484

@arXiv_csCL_bot@mastoxiv.page
2024-06-14 06:50:17

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
Jinchuan Tian, Yifan Peng, William Chen, Kwanghee Choi, Karen Livescu, Shinji Watanabe
arxiv.org/abs/2406.09282

@bourgwick@heads.social
2024-04-23 12:44:23

the construction crew next door has figured out a very efficient operation to maximize their impact where they do all their absolute loudest/noisiest/metal-grindy work starting as close to sunrise as possible, then get progressively quieter over the course of the day, ending in a gentle whisper, like the aural version of an andy goldsworthy sculpture. at least i'm guessing that's what they're doing based on how it sounds when they wake me up every fucking day. haven't asked. …

@theDuesentrieb@social.linux.pizza
2024-04-23 08:21:32

Eine neue Folge #StarTrekTagebuch
Diesmal mit viel Diplomatie und einem Exkurs zu #Behinderung in der #ScienceFiction

@arXiv_eessAS_bot@mastoxiv.page
2024-06-12 07:24:00

LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR
Zheshu Song, Jianheng Zhuo, Yifan Yang, Ziyang Ma, Shixiong Zhang, Xie Chen
arxiv.org/abs/2406.06619

@michabbb@social.vivaldi.net
2024-05-08 18:35:55

How Audio Speed Affects Transcription Accuracy: Benchmark Insights
#openai #whisper #api #ai

@arXiv_csSD_bot@mastoxiv.page
2024-06-13 09:37:37

This arxiv.org/abs/2406.05784 has been replaced.
initial toot: mastoxiv.page/@arXiv_csSD_…

@arXiv_csCL_bot@mastoxiv.page
2024-05-03 07:15:49

Efficient Compression of Multitask Multilingual Speech Models
Thomas Palmeira Ferraz
arxiv.org/abs/2405.00966 arxiv.o…

@arXiv_eessAS_bot@mastoxiv.page
2024-06-14 08:42:37

This arxiv.org/abs/2309.09548 has been replaced.
initial toot: mastoxiv.page/@arXiv_ees…

@arXiv_csSD_bot@mastoxiv.page
2024-06-12 08:50:13

This arxiv.org/abs/2310.17953 has been replaced.
initial toot: mastoxiv.page/@arXiv_csSD_…

@arXiv_eessAS_bot@mastoxiv.page
2024-04-30 08:37:30

This arxiv.org/abs/2309.12766 has been replaced.
initial toot: mastoxiv.page/@arXiv_ees…

@arXiv_csSD_bot@mastoxiv.page
2024-06-12 08:50:13

This arxiv.org/abs/2310.17953 has been replaced.
initial toot: mastoxiv.page/@arXiv_csSD_…

@arXiv_csSD_bot@mastoxiv.page
2024-05-07 07:35:11

Speech Technology Services for Oral History Research
Christoph Draxler, Henk van den Heuvel, Arjan van Hessen, Pavel Ircing, Jan Lehe\v{c}ka
arxiv.org/abs/2405.02333