Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs: record v1.4.3 publication closeout (#3522)

zhifu gao3c58cb56a565
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index 41db04e71..331b2ea8e 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -48,6 +48,8 @@ As of 2026-08-21 03:58 UTC, the ecosystem has 36,713 combined GitHub stars, or 5
- FunASR PR [#3519](https://github.com/modelscope/FunASR/pull/3519) merged as `eedd4e22d10dc2e81d9c2bb321edb3750253964b`. The release adds the optional `AutoModel(vad_model="silero-vad")` adapter with millisecond segments, threshold controls, 8/16 kHz input, ONNX mode, and bounded segment lengths. Large embedding sets with a known speaker count now use fixed-K clustering instead of dense spectral clustering.
- Exact-main validation passed 167 source tests, compileall, PEP 517 wheel/sdist builds, Twine, source-to-artifact diff checks, and isolated installs with no dependencies and full dependencies. The public wheel SHA-256 is `4b1491643a5bc6ccdd8acfc3ec438f9d9b9aaca8c2bf2d0e71f737dfc03025b9`; the sdist SHA-256 is `74a9a60eac4f05b7cba25d31bdc0f6bba5d70dbe9fd326291b362a5e425ba01a`.
- Signed tag `v1.4.3` peels exactly to the merge commit. The unique public [GitHub Release](https://github.com/modelscope/FunASR/releases/tag/v1.4.3) has the wheel, sdist, nine `runtime-llamacpp-v0.2.0` platform archives, and `SHA256SUMS-v1.4.3`, exactly 12 assets. Public PyPI and GitHub no-cache downloads matched every expected size and SHA-256, and a fresh public-wheel installation reported version 1.4.3.
+- FunASR PR [#3520](https://github.com/modelscope/FunASR/pull/3520) merged as verified commit `510a15ca3da463020cbffae93b6e3998ef159d41`, adding bilingual release guides, blog promotion, sitemap contracts, and this growth snapshot. Validation passed 88 Python product-site tests, 22 Playwright tests, and two identical exact-main builds of 104 HTML pages. Production release `20260821T041148Z` was atomically deployed to [the Chinese guide](https://www.funasr.com/blog/funasr-v1-4-3-pypi-release.html) and [English guide](https://www.funasr.com/en/blog/funasr-v1-4-3-pypi-release.html); archive SHA-256 is `b3610795e7f11471542c294bd1bbc982c08ca773e540752b47db0f74bacb8497`, and `20260817T054500Z` remains available for rollback.
+- Bilingual announcement [#3521](https://github.com/modelscope/FunASR/discussions/3521) publishes the pinned base and optional Silero install commands, exact artifact hashes, 12-asset boundary, verification evidence, and both website guides. The public discussion body was read back and matched the backed-up source exactly. A fresh audit of five public README files across Fun-ASR-Nano, SenseVoiceSmall, FSMN VAD, and Paraformer found them byte-identical to the prior snapshots and already using unpinned upgrade commands, so no unrelated model-card rewrite was needed.
### 2026-08-16 product-site attribution and claim audit