Record FunASR 1.4.16 release closeout

Signed-off-by: LauraGPT <[email protected]>

docs/community_growth_20k.md

@@ -433,6 +433,7 @@ Paste the Markdown output into launch notes, weekly community updates, or releas
 - [x] Keep recent Python GitHub release pages linked to runtime assets. On 2026-07-23, `v1.3.19` through `v1.3.26` were updated and verified to include a `Runtime downloads` section pointing to `runtime-llamacpp-v0.1.9`, including Windows Vulkan, Linux Vulkan, Windows CUDA, all nine prebuilt llama.cpp / GGUF assets, SHA-256 digests, and the matching PyPI install command. PR [#3398](https://github.com/modelscope/FunASR/pull/3398) merged as `9b918d74d7090b38211a6414c6ee08893a34afd4`; tag run [30000804161](https://github.com/modelscope/FunASR/actions/runs/30000804161) passed all nine builds plus the release job, and the published Windows Vulkan EXE depends only on the system Vulkan/Windows DLLs. The `scripts/update_release_runtime_downloads.py` guard and `tests/test_release_runtime_downloads.py` cover future tag releases.
 - [x] Update PyPI release description if needed. On 2026-07-23, the live PyPI `funasr 1.3.26` page was audited: its long description already comes from `README.md` and includes the current deployment-routing markers `OpenAI-compatible`, `/v1/audio/transcriptions`, `vllm`, `runtime-llamacpp-v0.1.8`, `GGUF`, and `funasr==1.3.26`. The package summary was prepared for the next PyPI publish by updating `setup.py` to `OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge runtime`, plus discovery keywords for `openai-compatible`, `websocket`, `vllm`, `gguf`, and `llama-cpp`; the currently published PyPI metadata remains `1.3.26` until the next weekly release upload.
 - [x] Publish and round-trip verify FunASR v1.4.0. On 2026-07-31, signed tag [`v1.4.0`](https://github.com/modelscope/FunASR/releases/tag/v1.4.0) was verified by GitHub against exact main `5f177695f238385d513415a0e20883b6411093be`. The public Release contains exactly 12 assets: wheel, sdist, all nine `runtime-llamacpp-v0.1.9` targets, and `SHA256SUMS-v1.4.0`; every GitHub digest matches the preserved staging bytes. Public PyPI contains only `funasr-1.4.0-py3-none-any.whl` and `funasr-1.4.0.tar.gz`; both were downloaded again with no-cache headers, matched exact-main size/SHA-256, and passed a fresh installed-wheel smoke covering version/import, the `vda_model` to `vad_model` guard, SenseVoice English normalization, and all four RWKV-BAT CUDA kernel sources. Release copy keeps the legacy WebSocket end-control fix scoped to tagged source rather than claiming it is part of the PyPI wheel.
+- [x] Publish, distribute, and close out FunASR v1.4.16. On 2026-09-18, release PR [#3719](https://github.com/modelscope/FunASR/pull/3719) merged as signed+DCO commit `904cd18681b8083de5e1039bd0ecebc4f49ede60`, and the verified signed tag [`v1.4.16`](https://github.com/modelscope/FunASR/releases/tag/v1.4.16) points to that exact commit. The public Release has exactly 12 assets: wheel, sdist, nine independently versioned `runtime-llamacpp-v0.2.6` archives, and `SHA256SUMS`; the separate Blackwell archive remains only on the runtime release. Public PyPI has exactly two files whose bytes match the GitHub assets: wheel `f95943f6a8111349a1b08907363b048a49e9cb9caa1e3afd8c92970d08bf450d` and sdist `1e2f8e3887fbc4b164cce40f73bf1324907da6ab59d1e8bf2add827f534c69e7`. The public install passed version/import, package-data, dependency, and CLI smoke checks. Downstream PR [#3721](https://github.com/modelscope/FunASR/pull/3721) merged as `acca7ea07091502480d784cc9e7f273df5e975ad` after 519 product-site tests, deterministic 117-page builds / 206-page validation, and green browser CI. Production release `20260918T065924Z` serves the bilingual guides at [`/blog/funasr-v1-4-16-submodel-device-release.html`](https://www.funasr.com/blog/funasr-v1-4-16-submodel-device-release.html) and [`/en/blog/funasr-v1-4-16-submodel-device-release.html`](https://www.funasr.com/en/blog/funasr-v1-4-16-submodel-device-release.html), indexed in both release/archive views and the sitemap. Announcement [#3720](https://github.com/modelscope/FunASR/discussions/3720) records the same boundaries. Six related Hugging Face and ModelScope cards were re-downloaded and audited; their only version floor is the compatible `funasr>=1.4.1` MLT-Nano requirement, while the others are unpinned, so no empty release-only card rewrite was made.
 - [ ] Update Hugging Face organization/model cards. The `FunAudioLLM/Fun-ASR-MLT-Nano-2512` README update is complete: HF PR [#5](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512/discussions/5) merged commit `3dd802bfb8a05dadc440c9d9fc84ecfc1e15c0ff`, and a 2026-07-23 live Hub download confirmed `main` now includes `python -m pip install -U "funasr>=1.3.26"` before optional demo-repo setup. Prepared README patches for `FunAudioLLM/Fun-ASR-Nano-2512` and `FunAudioLLM/SenseVoiceSmall` would add the same `funasr>=1.3.26` install floor, but the current `langgz` token still cannot write those model cards: direct upload fails with `403 Forbidden: pass create_pr=1`, and the Hub's suggested `--create-pr` path also fails at `preupload/main?create_pr=1` with `403 Forbidden: Authorization error`. Retry after model-card preupload/write permission is granted on those two repos.
 - [ ] Update ModelScope model cards and demos. On 2026-07-23, `scripts/sync_modelscope_model_cards.py` was added to generate and optionally upload current ModelScope README updates for `FunAudioLLM/Fun-ASR-Nano-2512` (`README.md`, `README_zh.md`) and `iic/SenseVoiceSmall` (`README.md`). The prepared cards add `python -m pip install -U "funasr>=1.3.26" modelscope` and `torch.cuda.is_available()` CUDA-wheel verification guidance, matching the clean H100 quickstart evidence. Prepared files are under `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/modelscope-card-sync-20260723/`. A live upload attempt with the existing 32-byte `.modelscope/credentials/session` failed: SDK uploads returned HTTP 400 from the ModelScope LFS batch API, and CLI upload reported `No credentials found`; the remaining blocker is a real ModelScope access token from `https://modelscope.cn/my/myaccesstoken`. Do not mark complete until those three ModelScope README files are uploaded and re-downloaded from the live model cards.
   - **2026-07-31 credential recheck:** `ind-gpu8` still has no `MODELSCOPE_API_TOKEN`, `MODELSCOPE_TOKEN`, `MODELSCOPE_ACCESS_TOKEN`, or ModelScope token file under the release config; only the previously rejected 32-byte `.modelscope/credentials/session` remains. The v1.4.0 SenseVoice/RWKV-BAT guidance must not overwrite live model cards until a real write-capable ModelScope token exists.