Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
Track SGLang Fun-ASR integration (#3058)
zhifu gao5193a9592a79
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.mdindex f3aa87963..6fd027ba3 100644--- a/docs/community_growth_20k.md+++ b/docs/community_growth_20k.md@@ -126,6 +126,7 @@ Set `GITHUB_TOKEN` when running this from CI or a shared network so GitHub's pub| Integration PR | Growth reason | Current maintainer action ||---|---|---|| `huggingface/transformers#46180` Fun-ASR-Nano model support | Makes Fun-ASR-Nano usable through the default HF API surface and model docs | Keep CI evidence current, address only actionable review threads, and avoid repeating maintainer pings unless new evidence appears. If `tests_processors` fails only in unrelated LightOnOCR cache setup, ask for a rerun once with the exact failing job. |+| `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 | Help keep benchmark claims precise: exact checkpoint/revision, dtype, GPU, concurrency, SeedTTS EN full-set comparison against Qwen3-ASR, and a copy-paste smoke command. || `ray-project/ray#64053` Ray Serve FunASR ASR example | Puts FunASR in production serving docs for teams already using Ray | Monitor review, answer questions quickly, and keep the example command aligned with the current OpenAI-compatible API behavior. || `huggingface/optimum-intel#1801` OpenVINO support | Helps CPU and edge users evaluate Fun-ASR on Intel hardware | Watch for CI or reviewer feedback, then validate a minimal inference path before promoting it in FunASR docs. |diff --git a/scripts/collect_growth_metrics.py b/scripts/collect_growth_metrics.pyindex 1eb9a1cc4..aec647564 100755--- a/scripts/collect_growth_metrics.py+++ b/scripts/collect_growth_metrics.py@@ -29,6 +29,7 @@ DEFAULT_TARGET_ADDITIONAL_STARS = 20000DEFAULT_TARGET_DATE = "2026-09-30"DEFAULT_INTEGRATION_PRS = ["huggingface/transformers#46180",+ "sgl-project/sglang-omni#898","ray-project/ray#64053","huggingface/optimum-intel#1801",]diff --git a/tests/test_collect_growth_metrics.py b/tests/test_collect_growth_metrics.pyindex 93b920208..70eb66121 100644--- a/tests/test_collect_growth_metrics.py+++ b/tests/test_collect_growth_metrics.py@@ -15,6 +15,12 @@ def load_growth_metrics_module():return 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++def test_collect_github_repo_metrics_splits_open_issues_and_pull_requests(monkeypatch):module = load_growth_metrics_module()