Skip to content

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

Update PyPI summary positioning (#3375)

zhifu gao459948691d9c
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index af3caebdb..bf8bb6aa9 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -359,7 +359,7 @@ Paste the Markdown output into launch notes, weekly community updates, or releas
- [x] Create a GitHub release focused on one sharp value proposition. On 2026-07-23, the latest GitHub release [`v1.3.26`](https://github.com/modelscope/FunASR/releases/tag/v1.3.26) was updated with the headline `Release focus: OpenAI-compatible ASR deployment`. The release now tells users this is the current Python release to install from PyPI, run the OpenAI-compatible transcription API, follow WebSocket realtime examples, or pair with the prebuilt llama.cpp / GGUF runtime assets. The top evidence block cites `python -m pip install -U "funasr==1.3.26"`, `/v1/audio/transcriptions`, `serve_realtime_ws.py`, `docs/vllm_guide.md`, the H100 Fun-ASR-Nano `vllm 0.19.1` smoke output, `funasr.com` 9-page patrol, and matching `runtime-llamacpp-v0.1.8` downloads for a self-contained `llama-funasr-*` binary.
- [x] Keep recent Python GitHub release pages linked to runtime assets. On 2026-07-23, `v1.3.19` through `v1.3.26` were verified to include a `Runtime downloads` section pointing to `runtime-llamacpp-v0.1.8`, including Linux Vulkan, Windows CUDA, all eight prebuilt llama.cpp / GGUF assets, and the matching PyPI install command. The `scripts/update_release_runtime_downloads.py` guard and `tests/test_release_runtime_downloads.py` cover future tag releases.
-- [ ] Update PyPI release description if needed.
+- [x] Update PyPI release description if needed. On 2026-07-23, the live PyPI `funasr 1.3.26` page was audited: its long description already comes from `README.md` and includes the current deployment-routing markers `OpenAI-compatible`, `/v1/audio/transcriptions`, `vllm`, `runtime-llamacpp-v0.1.8`, `GGUF`, and `funasr==1.3.26`. The package summary was prepared for the next PyPI publish by updating `setup.py` to `OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge runtime`, plus discovery keywords for `openai-compatible`, `websocket`, `vllm`, `gguf`, and `llama-cpp`; the currently published PyPI metadata remains `1.3.26` until the next weekly release upload.
- [ ] Update Hugging Face organization/model cards. The `FunAudioLLM/Fun-ASR-MLT-Nano-2512` README update is complete: HF PR [#5](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512/discussions/5) merged commit `3dd802bfb8a05dadc440c9d9fc84ecfc1e15c0ff`, and a 2026-07-23 live Hub download confirmed `main` now includes `python -m pip install -U "funasr>=1.3.26"` before optional demo-repo setup. Prepared README patches for `FunAudioLLM/Fun-ASR-Nano-2512` and `FunAudioLLM/SenseVoiceSmall` would add the same `funasr>=1.3.26` install floor, but the current `langgz` token still cannot write those model cards: direct upload fails with `403 Forbidden: pass create_pr=1`, and the Hub's suggested `--create-pr` path also fails at `preupload/main?create_pr=1` with `403 Forbidden: Authorization error`. Retry after model-card preupload/write permission is granted on those two repos.
- [ ] Update ModelScope model cards and demos.
- [ ] Update homepage hero and docs entry points.
diff --git a/setup.py b/setup.py
index 7572fa15c..066137e3a 100644
--- a/setup.py
+++ b/setup.py
@@ -116,8 +116,21 @@ setup(
url="https://github.com/modelscope/FunASR",
author="Speech Lab of Alibaba Group",
author_email="[email protected]",
- description="Industrial-grade speech recognition: 170x realtime, 50+ languages, speaker diarization, emotion detection.",
- keywords=["speech-recognition", "asr", "speaker-diarization", "vad", "pytorch", "whisper-alternative", "multilingual"],
+ description="OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge runtime.",
+ keywords=[
+ "speech-recognition",
+ "asr",
+ "speaker-diarization",
+ "vad",
+ "pytorch",
+ "whisper-alternative",
+ "multilingual",
+ "openai-compatible",
+ "websocket",
+ "vllm",
+ "gguf",
+ "llama-cpp",
+ ],
project_urls={
"Homepage": "https://github.com/modelscope/FunASR",
"Documentation": "https://modelscope.github.io/FunASR/",
diff --git a/tests/test_growth_plan_doc.py b/tests/test_growth_plan_doc.py
index ff812d0b1..021f3ef9c 100644
--- a/tests/test_growth_plan_doc.py
+++ b/tests/test_growth_plan_doc.py
@@ -171,3 +171,25 @@ def test_growth_plan_records_sharp_github_release_focus():
assert marker in text
assert "[ ] Create a GitHub release focused on one sharp value proposition" not in text
+
+
+def test_growth_plan_records_pypi_description_audit():
+ text = PLAN.read_text()
+
+ required_markers = [
+ "[x] Update PyPI release description if needed",
+ "PyPI `funasr 1.3.26`",
+ "long description already comes from `README.md`",
+ "`OpenAI-compatible`",
+ "`/v1/audio/transcriptions`",
+ "`vllm`",
+ "`runtime-llamacpp-v0.1.8`",
+ "`GGUF`",
+ "`funasr==1.3.26`",
+ "package summary was prepared for the next PyPI publish",
+ "OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge runtime",
+ ]
+ for marker in required_markers:
+ assert marker in text
+
+ assert "[ ] Update PyPI release description if needed" not in text
diff --git a/tests/test_pypi_metadata.py b/tests/test_pypi_metadata.py
new file mode 100644
index 000000000..5ba81d465
--- /dev/null
+++ b/tests/test_pypi_metadata.py
@@ -0,0 +1,34 @@
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+SETUP = ROOT / "setup.py"
+
+
+def _setup_text() -> str:
+ return SETUP.read_text(encoding="utf-8")
+
+
+def test_package_summary_matches_current_deployment_positioning():
+ text = _setup_text()
+
+ expected_summary = (
+ 'description="OpenAI-compatible speech recognition toolkit with '
+ 'WebSocket streaming, vLLM acceleration, and llama.cpp/GGUF edge '
+ 'runtime."'
+ )
+ assert expected_summary in text
+ assert "170x realtime" not in text
+
+
+def test_package_keywords_surface_deployment_discovery_terms():
+ text = _setup_text()
+
+ for keyword in [
+ '"openai-compatible"',
+ '"websocket"',
+ '"vllm"',
+ '"gguf"',
+ '"llama-cpp"',
+ ]:
+ assert keyword in text