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
Split issue and PR growth metrics (#3056)
zhifu gaoefe9b22a496e
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.mdindex 6c190c841..8a6b1e560 100644--- a/docs/community_growth_20k.md+++ b/docs/community_growth_20k.md@@ -34,7 +34,7 @@ This plan focuses on useful adoption work rather than vanity marketing: if more## Current campaign snapshot-As of 2026-06-30, the ecosystem has 34,623 combined GitHub stars, or 3,399 additional stars since the 31,224 baseline. The remaining gap to the +20,000 target is 16,601 stars by 2026-09-30.+As of 2026-06-30, the ecosystem has 34,625 combined GitHub stars, or 3,401 additional stars since the 31,224 baseline. The remaining gap to the +20,000 target is 16,599 stars by 2026-09-30.Keep this snapshot fresh during weekly planning. The ecosystem mode also reports the remaining gap, days left to 2026-09-30, and the required daily average:@@ -138,7 +138,7 @@ python scripts/collect_growth_metrics.pypython scripts/collect_growth_metrics.py --format json```-The script captures GitHub stars, forks, watchers, open issues, latest push time, and the current PyPI version using public APIs. Set `GITHUB_TOKEN` when running it from CI or a shared network to avoid public GitHub API rate limits. Paste the Markdown output into launch notes, weekly community updates, or release retrospectives so the 20k-star effort stays measurable.+The script captures GitHub stars, forks, watchers, open issues, open pull requests, latest push time, and the current PyPI version using public APIs. Set `GITHUB_TOKEN` when running it from CI or a shared network to avoid public GitHub API rate limits. Paste the Markdown output into launch notes, weekly community updates, or release retrospectives so the 20k-star effort stays measurable.## 30-day execution checklistdiff --git a/scripts/collect_growth_metrics.py b/scripts/collect_growth_metrics.pyindex 889c053bd..f15f1ec7b 100755--- a/scripts/collect_growth_metrics.py+++ b/scripts/collect_growth_metrics.py@@ -62,12 +62,19 @@ def github_headers() -> Dict[str, str]:def collect_github_repo_metrics(repo: str) -> Dict[str, Any]:owner_repo = repo.strip("/")github = fetch_json(f"https://api.github.com/repos/{owner_repo}", github_headers())+ open_pull_requests = len(+ fetch_json(f"https://api.github.com/repos/{owner_repo}/pulls?state=open&per_page=100", github_headers())+ )+ open_items = github.get("open_issues_count")+ open_issues = max((open_items or 0) - open_pull_requests, 0) if open_items is not None else Nonereturn {"repo": owner_repo,"stars": github.get("stargazers_count"),"forks": github.get("forks_count"),"watchers": github.get("subscribers_count"),- "open_issues": github.get("open_issues_count"),+ "open_items": open_items,+ "open_issues": open_issues,+ "open_pull_requests": open_pull_requests,"default_branch": github.get("default_branch"),"pushed_at": github.get("pushed_at"),"html_url": github.get("html_url"),@@ -227,6 +234,9 @@ def format_markdown(metrics: Dict[str, Any], star_goal: int) -> str:f"- GitHub forks: **{github.get('forks'):,}**" if github.get("forks") is not None else "- GitHub forks: n/a",f"- GitHub watchers: **{github.get('watchers'):,}**" if github.get("watchers") is not None else "- GitHub watchers: n/a",f"- Open issues: **{github.get('open_issues'):,}**" if github.get("open_issues") is not None else "- Open issues: n/a",+ f"- Open pull requests: **{github.get('open_pull_requests'):,}**"+ if github.get("open_pull_requests") is not None+ else "- Open pull requests: n/a",f"- PyPI package: **{pypi.get('package')} {pypi.get('version')}**",f"- Last GitHub push: `{github.get('pushed_at')}`","",@@ -256,8 +266,8 @@ def format_ecosystem_markdown(metrics: Dict[str, Any]) -> str:"","## Repositories","",- "| Repository | Stars | Forks | Open issues | Last push |",- "|---|---:|---:|---:|---|",+ "| Repository | Stars | Forks | Open issues | Open PRs | Last push |",+ "|---|---:|---:|---:|---:|---|",]for repo in ecosystem["repositories"]:lines.append(@@ -265,6 +275,7 @@ def format_ecosystem_markdown(metrics: Dict[str, Any]) -> str:f"{(repo.get('stars') or 0):,} | "f"{(repo.get('forks') or 0):,} | "f"{(repo.get('open_issues') or 0):,} | "+ f"{(repo.get('open_pull_requests') or 0):,} | "f"`{repo.get('pushed_at')}` |")lines.extend(diff --git a/tests/test_collect_growth_metrics.py b/tests/test_collect_growth_metrics.pyindex 9522d9068..466679037 100644--- a/tests/test_collect_growth_metrics.py+++ b/tests/test_collect_growth_metrics.py@@ -15,6 +15,33 @@ def load_growth_metrics_module():return module+def test_collect_github_repo_metrics_splits_open_issues_and_pull_requests(monkeypatch):+ module = load_growth_metrics_module()++ def fake_fetch_json(url, headers=None):+ if url == "https://api.github.com/repos/modelscope/FunASR":+ return {+ "stargazers_count": 18716,+ "forks_count": 3100,+ "subscribers_count": 210,+ "open_issues_count": 5,+ "default_branch": "main",+ "pushed_at": "2026-06-30T02:26:33Z",+ "html_url": "https://github.com/modelscope/FunASR",+ }+ if url == "https://api.github.com/repos/modelscope/FunASR/pulls?state=open&per_page=100":+ return [{"number": 3056}, {"number": 3057}]+ raise AssertionError(f"unexpected URL: {url}")++ monkeypatch.setattr(module, "fetch_json", fake_fetch_json)++ metrics = module.collect_github_repo_metrics("modelscope/FunASR")++ assert metrics["open_items"] == 5+ assert metrics["open_pull_requests"] == 2+ assert metrics["open_issues"] == 3++def test_collect_ecosystem_metrics_sums_repositories_and_target_gap(monkeypatch):module = load_growth_metrics_module()@@ -58,6 +85,8 @@ def test_collect_ecosystem_metrics_sums_repositories_and_target_gap(monkeypatch)}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 github_payloads[repo]@@ -90,6 +119,8 @@ def test_collect_ecosystem_metrics_calculates_daily_target(monkeypatch):module = load_growth_metrics_module()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/")stars = {@@ -185,6 +216,40 @@ def test_collect_integration_metrics_summarizes_pull_request_checks(monkeypatch)]+def test_format_ecosystem_markdown_includes_open_pull_requests():+ module = load_growth_metrics_module()+ metrics = {+ "collected_at_utc": "2026-06-30T02:30:00+00:00",+ "ecosystem": {+ "repositories": [+ {+ "repo": "modelscope/FunASR",+ "stars": 18716,+ "forks": 3100,+ "open_issues": 3,+ "open_pull_requests": 2,+ "pushed_at": "2026-06-30T02:26:33Z",+ "html_url": "https://github.com/modelscope/FunASR",+ }+ ],+ "total_stars": 18716,+ "baseline_stars": 31224,+ "added_stars": -12508,+ "target_additional_stars": 20000,+ "remaining_to_target": 32508,+ "target_date": "2026-09-30",+ "days_remaining": 92,+ "required_daily_average": 354,+ },+ "pypi": {"package": "funasr", "version": "1.3.14", "project_url": "https://pypi.org/project/funasr/"},+ }++ output = module.format_ecosystem_markdown(metrics)++ assert "| Repository | Stars | Forks | Open issues | Open PRs | Last push |" in output+ assert "| [modelscope/FunASR](https://github.com/modelscope/FunASR) | 18,716 | 3,100 | 3 | 2 |" in output++def test_main_outputs_ecosystem_json(monkeypatch):module = load_growth_metrics_module()@@ -196,6 +261,8 @@ def test_main_outputs_ecosystem_json(monkeypatch):}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 {