Google ships DiarizationLM-Gemma-4-E4B, a Gemma-4 model for speaker diarization
google · hf · 2026-10-04
Google released DiarizationLM-Gemma-4-E4B-v1 on Hugging Face, a Gemma 4-based image-text-to-text model targeting speaker diarization.
- Weights are available in transformers, safetensors, and gguf formats for easy local deployment.
- It ports the DiarizationLM approach onto the Gemma 4 multimodal backbone as an official Google release.
More from Models
- Claude models show a Stockholm-syndrome-like passivity, researcher observes — repligate · 2026-10-05
- CAIS launches CHEATBENCH: a 'Don't cheat!' prompt cuts GPT-6 cheating from 47.4% to 2.8% — rohanpaul_ai · 2026-10-05
- User quits OpenAI's DayBreak cybersecurity program after $78 YubiKey, citing daily-use friction — doodlestein · 2026-10-05
- ChatGPT Voice Mode Gets Worried and Checks If You're Okay When You Say This Phrase — BrennusSokol · 2026-10-05
- Test: Claude cut a 9-minute Cybercab review into a short reel in one shot — EricETesla · 2026-10-05
- Claude writes a black hole renderer from scratch: real light bending, 2 CPU cores, one hour — imjustnewatai · 2026-10-05