Skip to content

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

Infer ecosystem metrics from explicit repos (#3353)

zhifu gao9eee3095c87c
diff --git a/scripts/collect_growth_metrics.py b/scripts/collect_growth_metrics.py
index 26d14eca6..f67f0d786 100755
--- a/scripts/collect_growth_metrics.py
+++ b/scripts/collect_growth_metrics.py
@@ -982,8 +982,8 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--repos",
nargs="+",
- default=DEFAULT_ECOSYSTEM_REPOS,
- help="GitHub repositories for --ecosystem mode",
+ default=None,
+ help="GitHub repositories for --ecosystem or --issues mode; multiple explicit repos imply --ecosystem",
)
parser.add_argument("--ecosystem", action="store_true", help="Collect the four-repository FunASR ecosystem")
parser.add_argument("--integrations", action="store_true", help="Collect tracked external integration PRs")
@@ -1010,14 +1010,16 @@ def parse_args() -> argparse.Namespace:
def main() -> int:
args = parse_args()
+ repos = args.repos or DEFAULT_ECOSYSTEM_REPOS
+ ecosystem_mode = args.ecosystem or bool(args.repos and len(args.repos) > 1)
try:
if args.integrations:
metrics = collect_integration_metrics(args.integration_prs)
elif args.issues:
- metrics = collect_issue_metrics(args.repos)
- elif args.ecosystem:
+ metrics = collect_issue_metrics(repos)
+ elif ecosystem_mode:
metrics = collect_ecosystem_metrics(
- args.repos,
+ repos,
args.pypi_package,
args.baseline_stars,
args.target_additional_stars,
@@ -1035,7 +1037,7 @@ def main() -> int:
print(format_integration_markdown(metrics), end="")
elif args.issues:
print(format_issue_markdown(metrics), end="")
- elif args.ecosystem:
+ elif ecosystem_mode:
print(format_ecosystem_markdown(metrics), end="")
else:
print(format_markdown(metrics, args.star_goal), end="")
diff --git a/tests/test_collect_growth_metrics.py b/tests/test_collect_growth_metrics.py
index 846462cc0..032a7ce18 100644
--- a/tests/test_collect_growth_metrics.py
+++ b/tests/test_collect_growth_metrics.py
@@ -1642,6 +1642,64 @@ def test_main_outputs_ecosystem_json(monkeypatch):
assert payload["ecosystem"]["remaining_to_target"] == 16602
+def test_main_treats_explicit_multi_repos_as_ecosystem_json(monkeypatch):
+ module = load_growth_metrics_module()
+
+ repo_stars = {
+ "modelscope/FunASR": 18714,
+ "FunAudioLLM/Fun-ASR": 1318,
+ "FunAudioLLM/SenseVoice": 8718,
+ "modelscope/FunClip": 5872,
+ }
+
+ def fake_fetch_json(url, headers=None):
+ if url.endswith("/pulls?state=open&per_page=100"):
+ return []
+ if url.startswith("https://api.github.com/repos/"):
+ repo = url.removeprefix("https://api.github.com/repos/")
+ return {
+ "stargazers_count": repo_stars[repo],
+ "forks_count": 0,
+ "subscribers_count": 0,
+ "open_issues_count": 0,
+ "default_branch": "main",
+ "pushed_at": "2026-06-30T00:00:00Z",
+ "html_url": f"https://github.com/{repo}",
+ }
+ if url == "https://pypi.org/pypi/funasr/json":
+ return {"info": {"version": "1.3.14", "summary": "FunASR", "project_url": "https://pypi.org/project/funasr/"}}
+ raise AssertionError(f"unexpected URL: {url}")
+
+ monkeypatch.setattr(module, "fetch_json", fake_fetch_json)
+ monkeypatch.setattr(
+ sys,
+ "argv",
+ [
+ "collect_growth_metrics.py",
+ "--format",
+ "json",
+ "--repos",
+ "modelscope/FunASR",
+ "FunAudioLLM/Fun-ASR",
+ "FunAudioLLM/SenseVoice",
+ "modelscope/FunClip",
+ ],
+ )
+
+ with redirect_stdout(io.StringIO()) as stdout:
+ assert module.main() == 0
+
+ payload = json.loads(stdout.getvalue())
+ assert "github" not in payload
+ assert payload["ecosystem"]["total_stars"] == 34622
+ assert [repo["repo"] for repo in payload["ecosystem"]["repositories"]] == [
+ "modelscope/FunASR",
+ "FunAudioLLM/Fun-ASR",
+ "FunAudioLLM/SenseVoice",
+ "modelscope/FunClip",
+ ]
+
+
def test_main_outputs_integrations_json(monkeypatch):
module = load_growth_metrics_module()