BiliBili IndexTeam open-sources 150-language translation family with speech and 262K doc models
AdinaYakup · x · 2026-09-30
BiliBili's IndexTeam released Index-Translate, a multilingual translation model family built on Qwen3.5, now live on Hugging Face.
- Text translation: 2B / 9B / 35B-A3B (MoE, 3B active, preview) covering 150 languages; 2B/9B under Apache 2.0
- Speech: Index-Echo S2TT (speech-to-text) and S2ST (speech-to-speech) in 2B/9B sizes
- Specialized: Index-Homura for target-syllable-count translation (controlled dubbing); Index-Nailong for long documents up to 262K context
A notably complete open-source stack spanning text, speech, dubbing, and long-document translation.
Related event: Bilibili Open-Sources Index-Translate Models for 150 Languages(3 posts)→
More from Models
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Nathan Lambert calls out Ethan Mollick for 'selectively ignoring' Kimi in model comparisons — natolambert · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16