Skip to content

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

Record pinned release discussion (#3391)

zhifu gaocb6683ee7b0d
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index 6682641ef..be6229cc0 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -226,7 +226,7 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs
| `OpenBMB/VoxCPM#349` Windows CUDA installer with SenseVoice fallback | Puts SenseVoice into a 32k-star multilingual TTS app's Windows install and first-run ASR path as the fallback when local Parakeet/CUDA is unavailable | Current head `9f34141cc81e04028c4e62ac652f2a66dd453dfa` is dirty only in `app.py`; LauraGPT posted the conflict recipe and light validation at https://github.com/OpenBMB/VoxCPM/pull/349#issuecomment-4905293176. Wait for author rebase or maintainer action without duplicate comments. |
| `livekit/agents#6176` FunASR/SenseVoice realtime STT plugin | Opens a path into LiveKit's realtime voice-agent ecosystem where local STT is evaluated alongside hosted providers | Current head `9f995f7ee5fc` is mergeable and review-gated with all visible checks green or skipped. Fresh 2026-07-23 validation passed the 3 focused FunASR plugin tests, Ruff, format check, `uv lock --check`, `compileall`, and `git diff --check`; evidence was posted at https://github.com/livekit/agents/pull/6176#issuecomment-5051589686. Avoid duplicate pings and monitor for maintainer review on plugin scope, package metadata, or optional dependency expectations. |
| `datajuicer/data-juicer#938` HumanVBench audio/video operators | Places FunASR/SenseVoice-style speech understanding into a 6k-star data processing toolkit used to evaluate human-centric video and multimodal datasets | Current PR is open and mergeable but process-blocked while unit-test jobs are still waiting; LauraGPT posted the FunASR/SenseVoice dependency and validation follow-up at https://github.com/datajuicer/data-juicer/pull/938#issuecomment-4905235851. Wait for CI or maintainer feedback before adding more comments. |
-| `punkpeye/awesome-mcp-servers#7153` FunASR MCP server listing | Exposes FunASR to a high-star MCP discovery list used by agent-tool builders looking for local speech tools | Rebased across the upstream README conflict on 2026-07-23; head `6ed76450` is mergeable and `check-submission` passes. The referenced `ghcr.io/modelscope/funasr-mcp:0.1.1` image and official MCP Registry version are now public, but Glama still reports no quality score and an empty tool list; the remaining blocker is Glama resync/evaluation rather than package publication. Release evidence is at https://github.com/punkpeye/awesome-mcp-servers/pull/7153#issuecomment-5054229219; wait for the external sync and maintainer merge. |
+| `punkpeye/awesome-mcp-servers#7153` FunASR MCP server listing | Exposes FunASR to a high-star MCP discovery list used by agent-tool builders looking for local speech tools | Rebased across the upstream README conflict on 2026-07-23; head `6ed76450` is mergeable and `check-submission` passes. The referenced `ghcr.io/modelscope/funasr-mcp:0.1.1` image and official MCP Registry version are public. A live Glama score-page audit now identifies the exact remaining gate as `No Glama release`: a signed-in maintainer must claim the server if needed, configure and deploy the build on `/mcp/servers/modelscope/FunASR/admin/dockerfile`, wait for the build test, then use `Make Release` to publish a Glama version. Until that happens the API correctly remains `tools: []` with no quality score; this is not an automatic GitHub resync or package-publication failure. Release evidence remains at https://github.com/punkpeye/awesome-mcp-servers/pull/7153#issuecomment-5054229219; wait for the Glama release and upstream merge. |
| `Arindam200/awesome-ai-apps#250` FunASR Nebius voice note analyst | Places a runnable FunASR application in a 13k-star AI app catalog, showing a canonical OpenAI-compatible transcription path and an optional same-language structured brief without coupling transcription to the LLM provider | Head `5023cfd8ba20` is mergeable and both head checks are successful. Validation covers 55 tests on Python 3.10, 3.11, 3.12, and 3.14; Ruff and format checks; real H100 transcription with FunASR 1.3.14; and desktop/mobile Playwright runs without overflow or browser errors. GitHub labels the PR `UNSTABLE` because its generated potential merge commit has no status rollup even though the head rollup is successful and no required branch checks are reported; wait for maintainer review. |
| `zts212653/clowder-ai#1083` Qwen3-ASR service unification | Puts Qwen3-ASR into a user-facing local STT service slot by making it a `whisper-stt` backend variant instead of a separate, easier-to-misconfigure service | Merged on 2026-07-13 as `704bb735cae01be4bcd4089427bc6983c99a43a3` after fixes for Rosetta hardware detection, Qwen3-ASR install/server dispatch, async backend locking, temp WAV cleanup, and stale setup docs. The upstream service slot is already discoverable from the FunASR EN/ZH community integrations pages. |
| `run-llama/llama_index#21958` FunASR endpoint reader | Puts FunASR behind a LlamaIndex reader for OpenAI-compatible transcription endpoints used in RAG and agent pipelines | LauraGPT rechecked head `07a8599deaebe5e7a559d62174e7a872870c2f7e` at https://github.com/run-llama/llama_index/pull/21958#issuecomment-4905345545; author acknowledged the shared-reader pytest caveat at https://github.com/run-llama/llama_index/pull/21958#issuecomment-4905384536. Keep the endpoint contract clear and avoid forcing local `funasr` dependencies into the main package. |
@@ -368,7 +368,7 @@ Paste the Markdown output into launch notes, weekly community updates, or releas
### Week 4: Distribution and feedback
- [x] Share the release in relevant developer communities. On 2026-07-23, GitHub Discussion [`modelscope/FunASR#3376`](https://github.com/modelscope/FunASR/discussions/3376) was published in the `Announcements` category with the title `FunASR v1.3.26: OpenAI-compatible ASR deployment, vLLM, and llama.cpp runtime`. It routes readers to `funasr==1.3.26`, `/v1/audio/transcriptions`, WebSocket realtime examples, `docs/vllm_guide.md`, the H100 vLLM smoke evidence, `runtime-llamacpp-v0.1.8`, troubleshooting docs, and asks real app users to share hardware, model path, latency, and deployment friction.
-- [ ] Pin a GitHub discussion for the release. The release discussion exists at [`modelscope/FunASR#3376`](https://github.com/modelscope/FunASR/discussions/3376) with GraphQL node `D_kwDOIfjis84An-Vp` in the `Announcements` category. A 2026-07-23 GraphQL schema recheck found discussion mutations `createDiscussion`, `updateDiscussion`, `closeDiscussion`, `reopenDiscussion`, `deleteDiscussion`, and discussion-comment mutations, but still no `pinDiscussion` / `unpinDiscussion`; only `pinIssue`, `pinIssueComment`, and `pinEnvironment` are exposed. Pin manually in the GitHub Discussions UI or retry if GitHub adds a discussion pin mutation.
+- [x] Pin a GitHub discussion for the release. On 2026-07-23, [`modelscope/FunASR#3376`](https://github.com/modelscope/FunASR/discussions/3376) was pinned through the repository's authenticated Discussions admin UI. GitHub returned `Discussion has successfully been pinned`, and the admin controls now expose `Edit pinned discussion` and `Unpin discussion`; the `v1.3.26` OpenAI-compatible ASR, vLLM, and llama.cpp release story is therefore visible at the top of the public Discussions page.
- [x] Triage all new issues within 48 hours. On 2026-07-23, all four repositories were patrolled with the GitHub token on `ind-gpu8`: `modelscope/FunASR`, `FunAudioLLM/Fun-ASR`, `FunAudioLLM/SenseVoice`, and `modelscope/FunClip` all had `0` open pull requests; Fun-ASR, SenseVoice, and FunClip had `0` open issues. The only open FunASR issues were already triaged: #3302 is labeled `question` + `needs feedback` and is waiting for the reporter to retest the merged hotword/postprocess fix, while #3104 is labeled `enhancement` + `needs maintainer decision` and is waiting on release-scope confirmation for RL training code. No unlabelled or unowned open issue remained in the 48-hour window.
- [x] Convert top 3 support questions into docs. On 2026-07-23, the latest 80 FunASR issues were triaged into three repeat support blockers: install / hub / model-id selection (#3321, #3045, #3042, #2973, #2976), llama.cpp / GGUF / CUDA-Vulkan runtime packages (#3298, #3297, #3296, #3289, #3243), and realtime / VAD / vLLM / server output behavior (#3101, #3109, #3038, #3031, #2968, #2965). `docs/troubleshooting.md` and `docs/troubleshooting_zh.md` now start with a Top support questions section that maps those three issue clusters to the existing install, model-download, OpenAI-compatible server, WebSocket, and llama.cpp / GGUF FAQ anchors.
- [ ] Track stars, PyPI downloads, issue volume, and docs traffic. `collect_growth_metrics.py` now tracks GitHub stars, open issues, and open pull requests for the four core repositories and adds PyPIStats download windows for `funasr` as `downloads_last_7_days` and `downloads_last_30_days`. On 2026-07-23, the live PyPIStats window was refreshed at `116,407` downloads in 7 days and `442,556` downloads in 30 days through `2026-07-21`; successful runs now write `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/pypi-downloads-funasr.json`, and failed live runs fall back to that cache with status `stale_available` instead of dropping the download metric during SSL/429 outages. GitHub/PyPI tracking is now covered; docs traffic remains unavailable until an analytics credential or export is connected.
diff --git a/tests/test_growth_plan_doc.py b/tests/test_growth_plan_doc.py
index 8f5988409..7113b0074 100644
--- a/tests/test_growth_plan_doc.py
+++ b/tests/test_growth_plan_doc.py
@@ -208,26 +208,23 @@ def test_growth_plan_records_sharp_github_release_focus():
assert "[ ] Create a GitHub release focused on one sharp value proposition" not in text
-def test_growth_plan_records_discussion_pin_api_blocker():
+def test_growth_plan_records_discussion_pin_completion():
text = PLAN.read_text()
required_markers = [
- "[ ] Pin a GitHub discussion for the release",
+ "[x] Pin a GitHub discussion for the release",
"`modelscope/FunASR#3376`",
- "`D_kwDOIfjis84An-Vp`",
- "`Announcements` category",
- "`createDiscussion`",
- "`updateDiscussion`",
- "`closeDiscussion`",
- "`reopenDiscussion`",
- "no `pinDiscussion` / `unpinDiscussion`",
- "`pinIssue`",
- "`pinIssueComment`",
- "`pinEnvironment`",
+ "authenticated Discussions admin UI",
+ "`Discussion has successfully been pinned`",
+ "`Edit pinned discussion`",
+ "`Unpin discussion`",
+ "top of the public Discussions page",
]
for marker in required_markers:
assert marker in text
+ assert "[ ] Pin a GitHub discussion for the release" not in text
+
def test_growth_plan_records_issue_triage_completion():
text = PLAN.read_text()
@@ -337,9 +334,8 @@ def test_growth_plan_records_release_discussion_distribution():
"Announcements",
"`/v1/audio/transcriptions`",
"`runtime-llamacpp-v0.1.8`",
- "no `pinDiscussion` / `unpinDiscussion`",
- "`pinIssue`, `pinIssueComment`, and `pinEnvironment`",
- "[ ] Pin a GitHub discussion for the release",
+ "[x] Pin a GitHub discussion for the release",
+ "`Discussion has successfully been pinned`",
]
for marker in required_markers:
assert marker in text