# bilibili/Index-Translate

> A family of multilingual, multimodal translation models built on Qwen3.5, covering 150 languages for text, image, speech, and long-document translation, with a free OpenAI-compatible API.

- Magnitude: 2.3 out of 10 — Steady
- Stars: 1,534 total · +9 stars measured 2026-10-14, 07:47–09:27 UTC, ≈ 43 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-15 · Last push: 2026-10-12
- GitHub: https://github.com/bilibili/Index-Translate · Homepage: https://index-translate.bilibili.com · Page: https://gitnova.dev/en/r/bilibili/Index-Translate

## Useful for

- Translate text between 150 languages via the free OpenAI-compatible API.
- Translate images end-to-end without a separate OCR step.
- Dub speech into another language while cloning the original speaker's voice.

## Why it’s here

- Star-counter measurements on 2026-10-14 (UTC), 07:47–09:27: 1525 → 1534 stars (+9). This is the change over that interval.
- Estimated end-of-day forecast: about +43 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 57% of the previous week and a half.
- The repository is 29 days old and already has 1,534 stars.
- Top new repositories this month: #100.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 40
- Issues and pull requests: 23
- Watchers: 3
- Average over the last week: 81 per day
- Usual pace: 64 per day
- Stars in the last hour (measured): 5

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-15 … 2026-10-14: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 199, 112, 57, 144, 116, 140, 102, 120, 107, 120, 90, 67, 63, 79, 9

## Spotted in now

- Top new repositories this month: #100

## More in this category

1. **lyogavin/airllm** — 7.1 · Breakout · Language models · Jupyter Notebook · +241 stars measured 2026-10-14, 00:37–09:20 UTC, ≈ 651 by evening
   A library for inference and training of large language models on low-VRAM GPUs: it streams weights layer by layer from disk, letting 70B–671B models run on 4–12 GB of VRAM without quantization or distillation.
   Full card: https://gitnova.dev/en/r/lyogavin/airllm.md
2. **prabanta-dev/janas** — 6.6 · Early signal · Language models · C · +34 stars measured 2026-10-14, 00:37–09:20 UTC, ≈ 126 by evening
   Janas is a family of AI tools in C with no dependencies. Janas-LLM runs large MoE models (up to 80B, 48 GB) on a 32 GB laptop by streaming experts from NVMe SSD, and outperforms llama.cpp on all 13 tested models.
   Full card: https://gitnova.dev/en/r/prabanta-dev/janas.md
3. **open-webui/open-webui** — 5.5 · Breakout · Language models · Python · +34 stars measured 2026-10-14, 00:37–09:21 UTC, ≈ 162 by evening
   Open WebUI is a self-hosted web interface for AI models via Ollama and OpenAI-compatible APIs, with RAG, plugins, agents, and team collaboration.
   Full card: https://gitnova.dev/en/r/open-webui/open-webui.md
4. **microsoft/BitNet** — 4.9 · Breakout · Language models · C++ · +12 stars measured 2026-10-14, 00:37–09:21 UTC, ≈ 62 by evening
   Official inference framework for 1-bit LLMs (BitNet b1.58) with optimized kernels for CPU and GPU. Runs ternary models fast and losslessly, including a 100B model on a single CPU.
   Full card: https://gitnova.dev/en/r/microsoft/BitNet.md
5. **Niko1221/Strata** — 4.8 · Steady · Language models · C++ · +398 stars measured 2026-10-14, 00:38–09:21 UTC, ≈ 980 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-14 09:37 UTC, updated every 30 minutes.