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
Add funasr.com static page contract check (#3334)
zhifu gao51b6cad63b62
diff --git a/scripts/check_funasr_website_static.py b/scripts/check_funasr_website_static.pynew file mode 100755index 000000000..6aa831ed1--- /dev/null+++ b/scripts/check_funasr_website_static.py@@ -0,0 +1,119 @@+#!/usr/bin/env python3+"""Check public funasr.com pages for growth-critical copy regressions."""++from __future__ import annotations++import argparse+import sys+import urllib.request+from dataclasses import dataclass+++BASE_URL = "https://www.funasr.com"+++@dataclass(frozen=True)+class PageContract:+ required: tuple[str, ...]+ forbidden: tuple[str, ...] = ()+++PAGE_CONTRACTS: dict[str, PageContract] = {+ f"{BASE_URL}/ecosystem.html": PageContract(+ required=(+ "35K+",+ "/donors.html",+ "LiteLLM",+ "custom_openai",+ "54.3K stars",+ ),+ forbidden=("16K+",),+ ),+ f"{BASE_URL}/en/ecosystem.html": PageContract(+ required=(+ "35K+",+ "/en/donors.html",+ "LiteLLM",+ "custom_openai",+ "54.3K stars",+ ),+ forbidden=("16K+",),+ ),+ f"{BASE_URL}/donors.html": PageContract(+ required=("服务器", "www.funasr.com", "域名"),+ ),+ f"{BASE_URL}/en/donors.html": PageContract(+ required=("servers", "www.funasr.com", "domain"),+ ),+ f"{BASE_URL}/blog/funasr-cli-transcribe-command-line.html": PageContract(+ required=("推荐 funasr ≥ 1.3.26", "/donors.html"),+ forbidden=("1.3.10",),+ ),+ f"{BASE_URL}/en/blog/funasr-cli-transcribe-command-line.html": PageContract(+ required=("recommended funasr >= 1.3.26", "/en/donors.html"),+ forbidden=("1.3.10",),+ ),+ f"{BASE_URL}/blog/funasr-llama-cpp-whisper-cpp-alternative.html": PageContract(+ required=(+ "runtime-llamacpp-v0.1.8",+ "funasr-llamacpp-linux-x64-vulkan.tar.gz",+ "Vulkan / CUDA",+ "/donors.html",+ ),+ forbidden=("runtime-llamacpp-v0.1.1",),+ ),+ f"{BASE_URL}/en/blog/funasr-llama-cpp-whisper-cpp-alternative.html": PageContract(+ required=(+ "runtime-llamacpp-v0.1.8",+ "funasr-llamacpp-linux-x64-vulkan.tar.gz",+ "Vulkan / CUDA",+ "/en/donors.html",+ ),+ forbidden=("runtime-llamacpp-v0.1.1",),+ ),+}+++def validate_pages(pages: dict[str, str]) -> list[str]:+ failures: list[str] = []+ for url, contract in PAGE_CONTRACTS.items():+ text = pages.get(url)+ if text is None:+ failures.append(f"{url}: page was not fetched")+ continue+ for needle in contract.required:+ if needle not in text:+ failures.append(f"{url}: missing `{needle}`")+ for needle in contract.forbidden:+ if needle in text:+ failures.append(f"{url}: forbidden `{needle}`")+ return failures+++def fetch_pages(timeout: float) -> dict[str, str]:+ pages: dict[str, str] = {}+ for url in PAGE_CONTRACTS:+ with urllib.request.urlopen(url, timeout=timeout) as response:+ body = response.read()+ pages[url] = body.decode("utf-8", errors="replace")+ return pages+++def main(argv: list[str] | None = None) -> int:+ parser = argparse.ArgumentParser(description=__doc__)+ parser.add_argument("--timeout", type=float, default=20.0)+ args = parser.parse_args(argv)++ failures = validate_pages(fetch_pages(timeout=args.timeout))+ if failures:+ print("funasr.com static page contract failed:", file=sys.stderr)+ for failure in failures:+ print(f"- {failure}", file=sys.stderr)+ return 1++ print(f"funasr.com static page contract passed for {len(PAGE_CONTRACTS)} pages")+ return 0+++if __name__ == "__main__":+ raise SystemExit(main())diff --git a/tests/test_check_funasr_website_static.py b/tests/test_check_funasr_website_static.pynew file mode 100644index 000000000..c355ff378--- /dev/null+++ b/tests/test_check_funasr_website_static.py@@ -0,0 +1,85 @@+import importlib.util+import sys+from pathlib import Path+++ROOT = Path(__file__).resolve().parents[1]+SCRIPT = ROOT / "scripts" / "check_funasr_website_static.py"+++def _load_module():+ spec = importlib.util.spec_from_file_location("check_funasr_website_static", SCRIPT)+ module = importlib.util.module_from_spec(spec)+ sys.modules[spec.name] = module+ spec.loader.exec_module(module)+ return module+++def test_website_contract_accepts_current_public_copy():+ checker = _load_module()++ pages = {+ "https://www.funasr.com/ecosystem.html": """+ <div class="stat-num">35K+</div>+ <a href="/donors.html">功德榜</a>+ <a href="https://github.com/BerriAI/litellm">LiteLLM</a>+ <div>custom_openai</div>+ <div>54.3K stars</div>+ """,+ "https://www.funasr.com/en/ecosystem.html": """+ <div class="stat-num">35K+</div>+ <a href="/en/donors.html">Thanks</a>+ <a href="https://github.com/BerriAI/litellm">LiteLLM</a>+ <div>custom_openai</div>+ <div>54.3K stars</div>+ """,+ "https://www.funasr.com/donors.html": """+ 捐赠金额用于购买服务器与 <a href="https://www.funasr.com/">www.funasr.com</a> 域名+ """,+ "https://www.funasr.com/en/donors.html": """+ Donations helped purchase servers and the <a href="https://www.funasr.com/">www.funasr.com</a> domain.+ """,+ "https://www.funasr.com/blog/funasr-cli-transcribe-command-line.html": """+ pip install -U funasr # 推荐 funasr ≥ 1.3.26+ <a href="/donors.html">功德榜</a>+ """,+ "https://www.funasr.com/en/blog/funasr-cli-transcribe-command-line.html": """+ pip install -U funasr # recommended funasr >= 1.3.26+ <a href="/en/donors.html">Thanks</a>+ """,+ "https://www.funasr.com/blog/funasr-llama-cpp-whisper-cpp-alternative.html": """+ runtime-llamacpp-v0.1.8+ funasr-llamacpp-linux-x64-vulkan.tar.gz+ Vulkan / CUDA+ <a href="/donors.html">功德榜</a>+ """,+ "https://www.funasr.com/en/blog/funasr-llama-cpp-whisper-cpp-alternative.html": """+ runtime-llamacpp-v0.1.8+ funasr-llamacpp-linux-x64-vulkan.tar.gz+ Vulkan / CUDA+ <a href="/en/donors.html">Thanks</a>+ """,+ }++ assert checker.validate_pages(pages) == []+++def test_website_contract_reports_stale_runtime_and_star_copy():+ checker = _load_module()++ pages = {+ url: "" for url in checker.PAGE_CONTRACTS+ }+ pages["https://www.funasr.com/ecosystem.html"] = "16K+"+ pages[+ "https://www.funasr.com/blog/funasr-llama-cpp-whisper-cpp-alternative.html"+ ] = "runtime-llamacpp-v0.1.1"++ failures = checker.validate_pages(pages)++ assert any("ecosystem.html" in failure and "forbidden `16K+`" in failure for failure in failures)+ assert any(+ "funasr-llama-cpp-whisper-cpp-alternative.html" in failure+ and "forbidden `runtime-llamacpp-v0.1.1`" in failure+ for failure in failures+ )