The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestPyannotecommunity-1
PyannoteSpeech → Text

pyannote ships community-1 diarization pipeline

A new community edition of pyannote's open-source speaker diarization model lands on Hugging Face, targeting the "who spoke when" problem.

Apr 15, 2025
NotableOther
pyannote speaker-diarization-community-1

pyannote has published speaker-diarization-community-1, a new entry in its widely used family of open-source audio models. The pipeline tackles speaker diarization — the task of segmenting a recording into stretches of speech and attributing each to a distinct speaker, answering the question of "who spoke when."

Diarization is a quiet but essential layer in the modern speech stack. Transcription tells you what was said; diarization tells you who said it. The combination powers meeting notes, call-center analytics, interview tooling, and the speaker-labeled transcripts that have become standard in many consumer and enterprise products.

Why it matters

pyannote has become one of the default building blocks for open-source speech pipelines, and releases from the project tend to get picked up quickly by developers who need diarization they can run and audit themselves rather than calling a closed API.

  • The model targets the automatic speech recognition and audio processing domain.
  • It ships under a non-standard license, so teams should review the terms on the model card before production use.
  • As a "community" edition, it is positioned for broad open access alongside pyannote's other offerings.

The release arrives without published benchmark figures in the record, so practitioners will want to validate accuracy on their own audio conditions. Full details and usage instructions are available on the Hugging Face model page.

Sources

  • pyannote/speaker-diarization-community-1

    Hugging Face

    Visit
OlderIllustrious-XL v0.1 Arrives as Anime Image BaseUnknown · Text → Image · 2 years agoNewerJanus-4o-7B Adds Image Generation to 7B Multimodal AIFreedomIntelligence · Any-to-Any · last year

Get the model

Hugging Face

Specs

LicenseOTHER
Downloads4.8M
Likes4.8K

Modalities

Speech → Text

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More in Speech → Text

All Speech → Text →
Rumble-2-Flash
Reson8/Speech → TextRuns anywhere

Reson8's Rumble-2-Flash Puts ASR in 0.5B Params

A compact open speech recognition model aims to transcribe more than 40 languages without heavyweight infrastructure.

Nov 18, 2026
Haru-4B
Higurashi Ai/Any-to-AnyRuns on a laptop

Haru-4B Brings Full-Duplex Speech to Six Languages

A compact 4-billion-parameter model handles real-time, two-way voice conversation across six languages in a single system.

Nov 12, 2026
ServiceNow/Text → SpeechConsumer GPU

ServiceNow Debuts Apriel Voice 27B, an Open Speech Model

The 27-billion-parameter preview unifies text-to-speech, transcription, and reasoning in a single open model.

Oct 28, 2026