Skip to content

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

Track merged SGLang Omni Fun-ASR integration (#3328)

zhifu gao1068869b413d
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index b712ee859..12eb020ac 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -206,7 +206,7 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs
| `Kedreamix/Linly-Talker#151` FunASR link refresh | Keeps a 3.3k-star digital-avatar conversational system's ASR docs pointed at the current official FunASR repository, so users comparing Whisper and FunASR land on maintained setup docs | PR updates the root README and `ASR/README.md` references from `github.com/alibaba-damo-academy/FunASR` to `github.com/modelscope/FunASR`; monitor for maintainer acceptance without extra pings. |
| `huggingface/transformers#46180` Fun-ASR-Nano model support | Makes Fun-ASR-Nano usable through the default HF API surface and model docs | Head `ed68b42f9ea7` is ready for maintainer review: GitHub reports the PR mergeable, all active checks are successful or intentionally skipped, and `mergeStateStatus=BLOCKED` is now the review-required gate rather than a code or CI failure. The final review cleanup keeps feature extraction in Torch through `self.pad`, uses inherited batch-capable `decode`, removes the encoder-specific initializer, and preserves the pinned H100 checkpoint evidence for single and batch Chinese/English transcription with zero missing, unexpected, or mismatched keys. Avoid duplicate pings unless a new review thread or failing check appears. |
| `huggingface/transformers#47111` Qwen3-ASR hotword and language parsing fixes | Keeps the high-visibility Transformers Qwen3-ASR implementation aligned with upstream hotword/context behavior, language hints, and processor training paths used by downstream Fun-ASR-Nano/Qwen3-ASR adopters | The Qwen3-ASR slow job was explicitly rerun and reported no PR-specific failures on head `caf37300fc3d3333c3d7c2162a92a886e424eb1c`; the aggregate CI recap still has unrelated suite failures. Monitor for reviewer requests around hotword serialization, language parsing, and qwen3_asr processor tests before adding any FunASR-side comment. |
-| `sgl-project/sglang-omni#898` Fun-ASR serving support | Exposes Fun-ASR-Nano through a high-visibility serving runtime for ASR benchmarks and GPU deployment | The contributor-owned branch is currently dirty; LauraGPT already posted a concrete ASR benchmark rename/docs conflict recipe, and the author replied that conflicts will be resolved during merging. Wait for contributor or maintainer conflict resolution before adding more comments. |
+| `sgl-project/sglang-omni#1078` Fun-ASR serving support | Exposes Fun-ASR-Nano through a high-visibility serving runtime for ASR benchmarks and GPU deployment | Merged on 2026-07-18 after replacing the closed #898 branch. The merged PR includes Fun-ASR model runtime support, OpenAI-compatible serving, cookbook docs, SeedTTS benchmark tasks, unit tests, and review fixes from #1079. Public H200 SeedTTS EN full-set validation reports 1,088/1,088 samples, 0 failed, 1.71% corpus WER, 117.37 samples/s at concurrency 32, mean latency 0.271s, and mean RTF 0.0587; keep watching for follow-up issues rather than pinging the closed PR. |
| `vllm-project/vllm#42478` Qwen3-ASR streaming postprocessing | Improves the upstream Qwen3-ASR streaming path used by OpenAI-compatible transcription clients, so downstream apps can consume clean SSE transcript deltas without model-specific `language ...<asr_text>` cleanup | LauraGPT posted downstream validation guidance on 2026-07-08. CI is currently blocked only by vLLM's pre-run gate: the PR needs a maintainer `ready`/`verified` label or an author history of 4+ merged PRs (current log found 2), so wait for maintainer review rather than adding code-change comments; still watch for a no-space CJK regression. |
| `vllm-project/vllm#47729` MOSS-Transcribe-Diarize support | Expands vLLM's OpenAI-compatible `/v1/audio/transcriptions` route for long-form ASR with timestamps and speaker labels, creating another high-visibility comparison point for Qwen3-ASR / Fun-ASR-Nano-style serving behavior | PR is open and `mergeable=true` with `mergeable_state=blocked`; LauraGPT posted a non-blocking downstream ASR contract note at https://github.com/vllm-project/vllm/pull/47729#issuecomment-4912065897. Watch that `response_format=json` keeps the plain `{ "text": "..." }` shape stable, any future `segments` remain additive, CJK long-form audio stays covered, and the new model registration does not alter existing Qwen3-ASR request/response behavior. |
| `tenstorrent/tt-metal#49104` Qwen3-ASR Blackhole/P150 bringup | Opens a hardware-accelerated Qwen3-ASR path with an OpenAI-compatible `/v1/audio/transcriptions` server for Tenstorrent users evaluating speech workloads | PR is open, approved, and process-blocked rather than waiting on FunASR feedback; LauraGPT posted a non-blocking API-contract note at https://github.com/tenstorrent/tt-metal/pull/49104#issuecomment-4911526665. Track merge/release docs so downstream FunASR users can compare TT, CPU, vLLM, and H100 timing scopes correctly. |
diff --git a/scripts/collect_growth_metrics.py b/scripts/collect_growth_metrics.py
index 32bc4bf35..21227d1a9 100755
--- a/scripts/collect_growth_metrics.py
+++ b/scripts/collect_growth_metrics.py
@@ -31,7 +31,7 @@ DEFAULT_TARGET_ADDITIONAL_STARS = 20000
DEFAULT_TARGET_DATE = "2026-09-30"
DEFAULT_INTEGRATION_PRS = [
"huggingface/transformers#46180",
- "sgl-project/sglang-omni#898",
+ "sgl-project/sglang-omni#1078",
"yuekaizhang/Fun-ASR-vllm#21",
"ray-project/ray#64053",
"huggingface/optimum-intel#1801",
@@ -125,10 +125,6 @@ KNOWN_EXTERNAL_CHECK_FAILURES = {
}
}
KNOWN_REVIEW_GATES = {
- "sgl-project/sglang-omni#898": {
- "action": "wait for contributor conflict resolution",
- "reason": "Contributor-owned branch is dirty; conflict recipe already posted from the FunASR side",
- },
"punkpeye/awesome-mcp-servers#7153": {
"action": "wait for maintainer review",
"reason": "Glama listing and score badge are live",
@@ -504,6 +500,8 @@ def recommend_integration_action(
known_assisted_review_reason: Optional[str] = None,
) -> str:
if pull_request.get("state") != "open":
+ if pull_request.get("merged_at"):
+ return "merged / done"
return "archive"
if pull_request.get("draft"):
return "finish draft"
diff --git a/tests/test_collect_growth_metrics.py b/tests/test_collect_growth_metrics.py
index e17640fff..c30852fca 100644
--- a/tests/test_collect_growth_metrics.py
+++ b/tests/test_collect_growth_metrics.py
@@ -19,7 +19,8 @@ def load_growth_metrics_module():
def test_default_integration_prs_include_sglang_omni_fun_asr():
module = load_growth_metrics_module()
- assert "sgl-project/sglang-omni#898" in module.DEFAULT_INTEGRATION_PRS
+ assert "sgl-project/sglang-omni#1078" in module.DEFAULT_INTEGRATION_PRS
+ assert "sgl-project/sglang-omni#898" not in module.DEFAULT_INTEGRATION_PRS
def test_github_headers_falls_back_to_gh_auth_token(monkeypatch):
@@ -1066,38 +1067,45 @@ def test_recommend_integration_action_prioritizes_dirty_merge_state_over_pending
assert action == "resolve conflicts"
-def test_collect_integration_metrics_treats_empty_pending_status_as_review_gate(monkeypatch):
+def test_collect_integration_metrics_treats_merged_sglang_omni_as_completed(monkeypatch):
module = load_growth_metrics_module()
def fake_fetch_json(url, headers=None):
- if url == "https://api.github.com/repos/sgl-project/sglang-omni/pulls/898":
+ if url == "https://api.github.com/repos/sgl-project/sglang-omni/pulls/1078":
return {
- "number": 898,
+ "number": 1078,
"title": "Add Fun-ASR serving support",
- "state": "open",
+ "state": "closed",
"draft": False,
"mergeable": True,
- "mergeable_state": "blocked",
- "html_url": "https://github.com/sgl-project/sglang-omni/pull/898",
- "updated_at": "2026-06-30T04:48:08Z",
- "head": {"sha": "c081a79", "ref": "funasr-serving"},
+ "mergeable_state": "unknown",
+ "merged_at": "2026-07-18T15:11:15Z",
+ "html_url": "https://github.com/sgl-project/sglang-omni/pull/1078",
+ "updated_at": "2026-07-18T15:11:15Z",
+ "head": {"sha": "b6ea7ab1", "ref": "add-fun-asr"},
"base": {"ref": "main"},
"user": {"login": "PoTaTo-Mika"},
}
- if url == "https://api.github.com/repos/sgl-project/sglang-omni/commits/c081a79/status":
- return {"state": "pending", "statuses": []}
- if url == "https://api.github.com/repos/sgl-project/sglang-omni/commits/c081a79/check-runs?per_page=100":
- return {"total_count": 0, "check_runs": []}
+ if url == "https://api.github.com/repos/sgl-project/sglang-omni/commits/b6ea7ab1/status":
+ return {"state": "success", "statuses": []}
+ if url == "https://api.github.com/repos/sgl-project/sglang-omni/commits/b6ea7ab1/check-runs?per_page=100":
+ return {
+ "total_count": 2,
+ "check_runs": [
+ {"name": "unit", "status": "completed", "conclusion": "success"},
+ {"name": "cleanup - PR CI home on close", "status": "completed", "conclusion": "cancelled"},
+ ],
+ }
raise AssertionError(f"unexpected URL: {url}")
monkeypatch.setattr(module, "fetch_json", fake_fetch_json)
- metrics = module.collect_integration_metrics(["sgl-project/sglang-omni#898"])
+ metrics = module.collect_integration_metrics(["sgl-project/sglang-omni#1078"])
integration = metrics["integrations"][0]
- assert integration["checks"]["state"] == "unknown"
- assert integration["checks"]["pending_check_runs"] == []
- assert integration["next_action"] == "wait for contributor conflict resolution"
+ assert integration["state"] == "closed"
+ assert integration["checks"]["state"] == "failure"
+ assert integration["next_action"] == "merged / done"
def test_format_integration_markdown_includes_update_age_and_next_action():