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 Index Team Open-Sources Translation Models for 150 Languages(2 posts)→
More from Models
- Cohere launches Embed 5, claims state-of-the-art retrieval quality — aidangomez · 2026-09-30
- OpenAI grants Pro users 62,500 credits, worth roughly $2,500 — op7418 · 2026-09-30
- "Jev at Home": Open-Source Clone Runs Real-Time on Laptop CPU via Distillation — frjj-slm · 2026-09-30
- Gemini Can't Read Secondary Google Calendars or Custom Task Lists, Users Find — Here4Zipline · 2026-09-30
- Leak claims Google's Astra 6.1 arrives in October — iruletheworldmo · 2026-09-30
- Cohere launches Embed 5, a new family of enterprise embedding models — cohere · 2026-09-30