pyannoteAI
@pyannoteAI
Followers
370
Following
66
Media
3
Statuses
44
Make the most of conversational speech with state of the art voice AI
France
Joined April 2024
🎙️ We’re launching the official pyannoteAI Community Discord A place for developers, researchers, and Voice AI enthusiasts to: ✔ Get support & share knowledge ✔ Showcase projects & learn from each other ✔ Discuss trends shaping the Voice AI ecosystem https://t.co/HkdPhpkQVU
0
0
2
With 140k+ builders worldwide, we can’t wait to see how community-1 powers the next generation of voice AI. 👉 Try it today on Hugging Face 👉 Join our Release Seminar, Oct 7, 5pm CET Together, we’re building the foundation of Speaker Intelligence. https://t.co/qTb2Zi4ARl
discord.com
Discord is great for playing games and chilling with friends, or even building a worldwide community. Customize your own space to talk, play, and hang out.
0
1
2
And there’s more: 🔄 Switch from open-source to premium in just one line of code 💡 Train faster with optimized infrastructure As conversations happen everywhere, we are thrilled to announce that Community-1 is supported from Day 0 by our partners @argmaxinc @nexa_ai 🔥
1
0
4
This release is built on your feedback and tackles the two biggest pain points from our community: ✨ Best-in-class open-source diarization ⚡ Smooth alignment with STT https://t.co/BVC35yQgPH
huggingface.co
1
1
8
🚀 Will pyannoteAI keep improving its OSS toolkit? Absolutely. #OpenSource is where we come from — and today we’re proud to launch our brand-new model → community-1. https://t.co/ViJEpx4ANg
pyannote.ai
Community-1: Unleashing open-source diarization
1
3
6
🎹Introducing pyannote-audio 4⃣.0⃣ * 1 year * 100 commits * 17 contributors https://t.co/Xmxmq2wEuI
2
3
20
✨ Proud to announce Precision-2 — the next generation of our flagship diarization model. A release that truly sets a new standard for “who spoke when.” 🎙️
3
4
34
⚡ All in one API, production-ready. Whether you’re building transcription tools, dubbing workflows, training voice models, or call monitoring — Precision-2 combines out-of-the-box accuracy with developer control.
1
0
1
🔹 Features developers have been waiting for – exclusive: true → clean STT ↔ diarization alignment – minSpeakers / maxSpeakers → control speaker bounds – Per-segment confidence vectors → faster, targeted QA
1
0
1
🔹 Accuracy where it matters most – Correct speaker count in 70% of tough cases (vs 50%) → less confusion, fewer edits – Smarter overlap detection: +5% vs Precision-1, +15% vs OSS
1
0
1
For years, our open-source pyannote-audio has been the de facto reference. With the Precision series, we push further — blending academic research, large-scale training & customer feedback.
1
0
2
✨ Proud to announce Precision-2 — the next generation of our flagship diarization model. A release that truly sets a new standard for “who spoke when.” 🎙️
3
4
34
The flagship @pyannoteAI speaker diarization model is now on Argmax SDK! We are thrilled to bring the most accurate speaker diarization model on device, where conversations happen. Same familiar APIs, no code changes required to upgrade from the open-source pyannote model.
1
12
48
Despite the impressive accuracy of open-source pyannote-3.1 models, we have heard our customers yearn for even higher accuracy. Today, we bring the most advanced speaker diarization model on device with Argmax SDK by partnering with @pyannoteAI:
argmaxinc.com
Argmax partners with pyannoteAI, the industry-leading speaker recognition technology company. pyannoteAI's flagship commercial model is now available for on-device deployment with Argmax SDK. Our...
1
2
6
@argmaxinc 👉Discover more about the partnership: https://t.co/mXjAAnXLca 👉Get in touch:
0
0
3
Where conversations happen, speaker intelligence should follow. pyannoteAI is now available on-device, thanks to our partnership with @argmaxinc 🎉Run our most accurate speaker diarization models at the edge. 📷 More in the comments #VoiceAI #PrivacyFirst #Diarization #AI
2
4
8
Discover more about the partnership: https://t.co/mXjAAnXLca Get in touch:
0
0
0
Learn about speaker diarization from the pyannote himself (our chief science officer).
... in which I'll talk about my decade-old love for speaker diarization and the loss functions used to train underlying neural networks
0
1
4