mirror of
https://github.com/modelscope/FunASR.git
synced 2026-10-12 02:19:18 +00:00
486 lines
18 KiB
Python
486 lines
18 KiB
Python
import re
|
||
import shlex
|
||
from pathlib import Path
|
||
|
||
import pytest
|
||
|
||
ROOT = Path(__file__).resolve().parents[1]
|
||
|
||
|
||
DOCS_WITH_CURRENT_FUNASR_INSTALL = [
|
||
"examples/industrial_data_pretraining/fun_asr_nano/docs/finetune.md",
|
||
"examples/industrial_data_pretraining/fun_asr_nano/docs/finetune_zh.md",
|
||
]
|
||
|
||
PUBLIC_DOCS_SHOULD_USE_CURRENT_HOSTS = [
|
||
"benchmarks/benchmark_pipeline_cer.md",
|
||
"docs/installation/installation.md",
|
||
"docs/installation/installation_zh.md",
|
||
"model_zoo/modelscope_models.md",
|
||
"model_zoo/readme.md",
|
||
"runtime/docs/SDK_advanced_guide_offline.md",
|
||
"runtime/docs/SDK_advanced_guide_offline_en.md",
|
||
"runtime/docs/SDK_advanced_guide_offline_en_zh.md",
|
||
"runtime/docs/SDK_advanced_guide_offline_gpu.md",
|
||
"runtime/docs/SDK_advanced_guide_offline_gpu_zh.md",
|
||
"runtime/docs/SDK_advanced_guide_offline_zh.md",
|
||
"runtime/docs/SDK_advanced_guide_online.md",
|
||
"runtime/docs/SDK_advanced_guide_online_zh.md",
|
||
"runtime/python/grpc/Readme.md",
|
||
"runtime/python/libtorch/README.md",
|
||
"runtime/python/onnxruntime/README.md",
|
||
"runtime/python/websocket/README.md",
|
||
"docs/m2met2/Baseline.md",
|
||
"examples/industrial_data_pretraining/monotonic_aligner/README_zh.md",
|
||
"examples/industrial_data_pretraining/sense_voice/README.md",
|
||
"examples/industrial_data_pretraining/sense_voice/README_zh.md",
|
||
"examples/industrial_data_pretraining/sense_voice/README_ja.md",
|
||
"runtime/html5/readme.md",
|
||
"runtime/html5/readme_zh.md",
|
||
]
|
||
|
||
PUBLIC_ENTRYPOINTS_SHOULD_USE_CURRENT_REPO_URLS = [
|
||
"model_zoo/modelscope_models.md",
|
||
"model_zoo/modelscope_models_zh.md",
|
||
"model_zoo/readme.md",
|
||
"web-pages/src/views/home/index.vue",
|
||
"web-pages/src/views/home/lxwjzxfw.vue",
|
||
"web-pages/src/views/home/sstx.vue",
|
||
"runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-en.sh",
|
||
"runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh",
|
||
"runtime/deploy_tools/funasr-runtime-deploy-online-cpu-zh.sh",
|
||
"runtime/docs/SDK_tutorial.md",
|
||
"runtime/docs/SDK_tutorial_en.md",
|
||
"runtime/docs/SDK_tutorial_en_zh.md",
|
||
"runtime/docs/SDK_tutorial_online.md",
|
||
"runtime/docs/SDK_tutorial_online_zh.md",
|
||
"runtime/docs/SDK_tutorial_zh.md",
|
||
"runtime/python/http/server.py",
|
||
"runtime/python/libtorch/setup.py",
|
||
"runtime/python/onnxruntime/setup.py",
|
||
]
|
||
|
||
|
||
def test_current_funasr_install_commands_are_quoted():
|
||
for relpath in DOCS_WITH_CURRENT_FUNASR_INSTALL:
|
||
text = (ROOT / relpath).read_text()
|
||
assert '"funasr>=1.3.26"' in text
|
||
assert "funasr>=1.3.0" not in text
|
||
assert not re.search(r"pip install funasr>=", text)
|
||
|
||
|
||
@pytest.mark.parametrize("relpath", ["docs/vllm_guide.md", "docs/vllm_guide_zh.md"])
|
||
def test_vllm_service_install_uses_a_pinned_checkout(relpath):
|
||
text = (ROOT / relpath).read_text()
|
||
blocks = re.findall(r"^```bash\n(.*?)^```", text, re.M | re.S)
|
||
install = blocks[0]
|
||
assert 'python -m pip install "vllm==0.19.1"' in install
|
||
assert "git clone https://github.com/modelscope/FunASR.git FunASR-vllm" in install
|
||
assert re.search(r"^git checkout --detach [0-9a-f]{40}$", install, re.M)
|
||
assert "python -m pip install -e ." in install
|
||
assert "python -m pip check" in install
|
||
assert not re.search(r"pip install.*funasr[>=]", install)
|
||
|
||
|
||
def test_vllm_install_translations_have_identical_commands():
|
||
recipes = []
|
||
for relpath in ("docs/vllm_guide.md", "docs/vllm_guide_zh.md"):
|
||
text = (ROOT / relpath).read_text()
|
||
install = re.findall(r"^```bash\n(.*?)^```", text, re.M | re.S)[0]
|
||
recipes.append([
|
||
tokens for line in install.splitlines()
|
||
if (tokens := shlex.split(line, comments=True))
|
||
])
|
||
assert recipes[0] == recipes[1]
|
||
|
||
|
||
def test_fun_asr_nano_finetune_zh_uses_canonical_filename():
|
||
docs_dir = ROOT / "examples/industrial_data_pretraining/fun_asr_nano/docs"
|
||
assert (docs_dir / "finetune_zh.md").exists()
|
||
assert "fintune_zh.md" not in (docs_dir / "finetune.md").read_text()
|
||
|
||
|
||
def test_public_docs_use_current_repository_and_docs_hosts():
|
||
for relpath in PUBLIC_DOCS_SHOULD_USE_CURRENT_HOSTS:
|
||
text = (ROOT / relpath).read_text()
|
||
assert "github.com/alibaba/FunASR" not in text
|
||
assert "alibaba-damo-academy.github.io/FunASR" not in text
|
||
|
||
|
||
def test_public_entrypoints_use_current_repository_urls():
|
||
forbidden = [
|
||
"github.com/alibaba-damo-academy/FunASR",
|
||
"raw.githubusercontent.com/alibaba-damo-academy/FunASR",
|
||
]
|
||
|
||
for relpath in PUBLIC_ENTRYPOINTS_SHOULD_USE_CURRENT_REPO_URLS:
|
||
text = (ROOT / relpath).read_text()
|
||
for marker in forbidden:
|
||
assert marker not in text
|
||
|
||
|
||
def test_troubleshooting_faq_is_linked_from_readmes():
|
||
readme_links = [
|
||
("README.md", "./docs/troubleshooting.md"),
|
||
("README_zh.md", "./docs/troubleshooting_zh.md"),
|
||
]
|
||
|
||
for readme, link in readme_links:
|
||
text = (ROOT / readme).read_text()
|
||
assert link in text
|
||
|
||
|
||
def test_troubleshooting_faq_covers_common_install_and_deploy_failures():
|
||
docs = [
|
||
(ROOT / "docs/troubleshooting.md").read_text(),
|
||
(ROOT / "docs/troubleshooting_zh.md").read_text(),
|
||
]
|
||
required_markers = [
|
||
"torch",
|
||
"torchaudio",
|
||
"ModelScope",
|
||
"Hugging Face",
|
||
"funasr-server",
|
||
"/v1/audio/transcriptions",
|
||
"WebSocket",
|
||
"llama.cpp",
|
||
"GGUF",
|
||
"Deployment Help",
|
||
]
|
||
|
||
for text in docs:
|
||
for marker in required_markers:
|
||
assert marker in text
|
||
|
||
|
||
def test_tutorials_keep_model_license_boundaries_model_card_specific():
|
||
docs = {
|
||
"en": (ROOT / "docs/tutorial/README.md").read_text(),
|
||
"zh": (ROOT / "docs/tutorial/README_zh.md").read_text(),
|
||
}
|
||
|
||
assert "Each model weight has its own license" in docs["en"]
|
||
assert "model card explicitly links" in docs["en"]
|
||
assert "每个模型权重都有各自的许可" in docs["zh"]
|
||
assert "模型卡明确链接" in docs["zh"]
|
||
|
||
for text in docs.values():
|
||
assert "自由使用、复制、修改和分享FunASR模型" not in text
|
||
assert "free to use, copy, modify, and share FunASR models" not in text
|
||
|
||
|
||
def test_public_docs_do_not_advertise_stale_release_or_star_copy():
|
||
checked_docs = [
|
||
"docs/repository_roles.md",
|
||
"docs/repository_roles_zh.md",
|
||
"docs/blog_whisper_vs_funasr_zh.md",
|
||
"runtime/llama.cpp/README.md",
|
||
]
|
||
forbidden = [
|
||
"GitHub tags go up to `v1.3.13`",
|
||
"PyPI has published `1.3.14`",
|
||
"GitHub tag 至 `v1.3.13`",
|
||
"PyPI 已发布 `1.3.14`",
|
||
"（16K+ stars）",
|
||
"runtime-llamacpp-v0.1.7",
|
||
]
|
||
|
||
for relpath in checked_docs:
|
||
text = (ROOT / relpath).read_text()
|
||
for marker in forbidden:
|
||
assert marker not in text
|
||
|
||
|
||
def test_readme_model_tables_use_current_modelscope_entries():
|
||
readmes = [
|
||
(ROOT / "README.md").read_text(),
|
||
(ROOT / "README_zh.md").read_text(),
|
||
(ROOT / "README_ja.md").read_text(),
|
||
(ROOT / "README_ko.md").read_text(),
|
||
]
|
||
|
||
current_entries = [
|
||
"models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
]
|
||
stale_entries = [
|
||
"models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
]
|
||
|
||
for text in readmes:
|
||
assert current_entries[0] in text
|
||
assert stale_entries[0] not in text
|
||
|
||
for text in readmes[:2]:
|
||
for marker in current_entries:
|
||
assert marker in text
|
||
for marker in stale_entries:
|
||
assert marker not in text
|
||
|
||
|
||
def test_model_zoo_tables_use_current_paraformer_modelscope_entry():
|
||
docs = [
|
||
(ROOT / "model_zoo/modelscope_models.md").read_text(),
|
||
(ROOT / "model_zoo/modelscope_models_zh.md").read_text(),
|
||
(ROOT / "model_zoo/readme.md").read_text(),
|
||
]
|
||
|
||
current = (
|
||
"models/iic/"
|
||
"speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
|
||
"/summary"
|
||
)
|
||
stale = (
|
||
"models/damo/"
|
||
"speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
|
||
"/summary"
|
||
)
|
||
|
||
for text in docs:
|
||
assert current in text
|
||
assert stale not in text
|
||
|
||
|
||
def test_full_modelscope_tables_use_current_core_entries():
|
||
docs = [
|
||
(ROOT / "model_zoo/modelscope_models.md").read_text(),
|
||
(ROOT / "model_zoo/modelscope_models_zh.md").read_text(),
|
||
]
|
||
|
||
current_entries = [
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
]
|
||
stale_entries = [
|
||
"models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
]
|
||
|
||
for text in docs:
|
||
for marker in current_entries:
|
||
assert marker in text
|
||
for marker in stale_entries:
|
||
assert marker not in text
|
||
|
||
|
||
def test_runtime_benchmark_docs_use_current_core_modelscope_entries():
|
||
docs = [
|
||
(ROOT / "benchmarks/benchmark_pipeline_cer.md").read_text(),
|
||
(ROOT / "runtime/docs/benchmark_libtorch.md").read_text(),
|
||
(ROOT / "runtime/docs/benchmark_onnx.md").read_text(),
|
||
(ROOT / "runtime/docs/benchmark_onnx_cpp.md").read_text(),
|
||
]
|
||
|
||
current_entries = [
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/iic/speech_fsmn_vad_zh-cn-16k-common-onnx/summary",
|
||
"models/iic/punc_ct-transformer_zh-cn-common-vocab272727-onnx/summary",
|
||
]
|
||
stale_entries = [
|
||
entry.replace("models/iic/", "models/damo/") for entry in current_entries
|
||
]
|
||
|
||
combined = "\n".join(docs)
|
||
for marker in current_entries:
|
||
assert marker in combined
|
||
for marker in stale_entries:
|
||
assert marker not in combined
|
||
|
||
|
||
def test_model_zoo_landing_tables_link_huggingface_repos():
|
||
docs = [
|
||
(
|
||
(ROOT / "model_zoo/readme.md").read_text(),
|
||
[
|
||
"https://huggingface.co/funasr/paraformer-zh",
|
||
"https://huggingface.co/funasr/paraformer-zh-streaming",
|
||
"https://huggingface.co/funasr/ct-punc",
|
||
"https://huggingface.co/funasr/fsmn-vad",
|
||
],
|
||
),
|
||
(
|
||
(ROOT / "model_zoo/readme_zh.md").read_text(),
|
||
[
|
||
"https://huggingface.co/funasr/paraformer-zh",
|
||
"https://huggingface.co/funasr/paraformer-zh-streaming",
|
||
],
|
||
),
|
||
]
|
||
|
||
for text, required_hf_links in docs:
|
||
for link in required_hf_links:
|
||
assert link in text
|
||
|
||
|
||
def test_model_zoo_landing_tables_use_current_core_modelscope_entries():
|
||
docs = [
|
||
(
|
||
(ROOT / "model_zoo/readme.md").read_text(),
|
||
[
|
||
"models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
],
|
||
[
|
||
"models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
"models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
|
||
"models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
|
||
],
|
||
),
|
||
(
|
||
(ROOT / "model_zoo/readme_zh.md").read_text(),
|
||
[
|
||
"models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
],
|
||
[
|
||
"models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
|
||
"models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
|
||
],
|
||
),
|
||
]
|
||
|
||
for text, current_entries, stale_entries in docs:
|
||
for marker in current_entries:
|
||
assert marker in text
|
||
for marker in stale_entries:
|
||
assert marker not in text
|
||
|
||
|
||
def test_readme_model_tables_surface_public_gguf_entries():
|
||
readmes = [
|
||
(ROOT / "README.md").read_text(),
|
||
(ROOT / "README_zh.md").read_text(),
|
||
(ROOT / "README_ja.md").read_text(),
|
||
(ROOT / "README_ko.md").read_text(),
|
||
]
|
||
|
||
for text in readmes:
|
||
assert "https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-GGUF" in text
|
||
assert "https://huggingface.co/FunAudioLLM/SenseVoiceSmall-GGUF" in text
|
||
assert "https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-GGUF" not in text
|
||
|
||
|
||
def test_top_level_readmes_surface_current_release_and_edge_runtime():
|
||
readmes = {
|
||
name: (ROOT / name).read_text()
|
||
for name in ("README.md", "README_zh.md", "README_ja.md", "README_ko.md")
|
||
}
|
||
|
||
for name, text in readmes.items():
|
||
assert 'python -m pip install -U "funasr==1.4.14"' in text, name
|
||
assert "https://github.com/modelscope/FunASR/releases/tag/v1.4.14" in text, name
|
||
assert "runtime-llamacpp-v0.2.6" in text, name
|
||
|
||
assert "https://www.funasr.com/en/deploy/llama-cpp.html" in readmes["README.md"]
|
||
assert "https://www.funasr.com/deploy/llama-cpp.html" in readmes["README_zh.md"]
|
||
for name in ("README_ja.md", "README_ko.md"):
|
||
assert "https://www.funasr.com/en/deploy/llama-cpp.html" in readmes[name]
|
||
|
||
for name in ("README.md", "README_zh.md"):
|
||
text = readmes[name]
|
||
for asset in (
|
||
"funasr-llamacpp-linux-x64-vulkan.tar.gz",
|
||
"funasr-llamacpp-windows-x64-vulkan.zip",
|
||
"funasr-llamacpp-windows-x64-cuda.zip",
|
||
"funasr-llamacpp-windows-x64-cuda-blackwell.zip",
|
||
):
|
||
assert (
|
||
f"releases/download/runtime-llamacpp-v0.2.6/{asset}" in text
|
||
), name
|
||
assert "releases/download/runtime-llamacpp-v0.2.1/" not in text, name
|
||
|
||
|
||
def test_top_level_readme_news_stays_concise():
|
||
headings = {
|
||
"README.md": "## What's new",
|
||
"README_zh.md": "## 最新动态",
|
||
"README_ja.md": "## 最新情報",
|
||
"README_ko.md": "## 최신 소식",
|
||
}
|
||
|
||
for name, heading in headings.items():
|
||
text = (ROOT / name).read_text()
|
||
news = text.split(heading, 1)[1].split("\n---", 1)[0]
|
||
assert news.count("\n- ") <= 5, name
|
||
assert "https://github.com/modelscope/FunASR/releases" in news, name
|
||
|
||
|
||
def test_repository_roadmap_tracks_current_delivery_and_open_work():
|
||
docs = [
|
||
(ROOT / "docs/repository_roles.md").read_text(),
|
||
(ROOT / "docs/repository_roles_zh.md").read_text(),
|
||
]
|
||
|
||
for text in docs:
|
||
assert "1.4.14" in text
|
||
assert "v1.3.26" not in text
|
||
assert "runtime-llamacpp-v0.2.6" in text
|
||
assert "MOSS-Transcribe-Diarize" in text
|
||
assert "https://github.com/modelscope/FunASR/issues/3496" in text
|
||
assert "https://github.com/modelscope/FunASR/issues/3528" in text
|
||
assert "https://github.com/modelscope/FunASR/issues/3479" in text
|
||
assert "https://github.com/huggingface/transformers/pull/46180" in text
|
||
|
||
assert "speaker identities" not in docs[0]
|
||
assert "说话人身份识别" not in docs[1]
|
||
|
||
|
||
def test_repository_roadmap_exposes_live_contribution_entry_points():
|
||
docs = [
|
||
(ROOT / "docs/repository_roles.md").read_text(),
|
||
(ROOT / "docs/repository_roles_zh.md").read_text(),
|
||
]
|
||
live_queries = [
|
||
"is%3Aissue+is%3Aopen+label%3A%22help+wanted%22",
|
||
"is%3Aissue+is%3Aopen+label%3A%22ready+for+PR%22",
|
||
]
|
||
|
||
for text in docs:
|
||
for query in live_queries:
|
||
assert query in text
|
||
assert "needs feedback" in text
|
||
|
||
assert "exact commit" in docs[0]
|
||
assert "acceptance evidence" in docs[0]
|
||
assert "exact commit" in docs[1]
|
||
assert "验收证据" in docs[1]
|
||
|
||
contributing = (ROOT / "CONTRIBUTING.md").read_text()
|
||
assert "## Find a task" in contributing
|
||
for query in live_queries:
|
||
assert query in contributing
|
||
assert "needs feedback" in contributing
|
||
|
||
|
||
def test_realtime_demo_documents_partial_and_hotword_boundaries():
|
||
text = (
|
||
ROOT
|
||
/ "examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md"
|
||
).read_text()
|
||
|
||
required = [
|
||
"data.sentences.map",
|
||
"data.partial || \"\"",
|
||
"partial_start_ms",
|
||
"--partial-window-sec",
|
||
"不是确定性文本替换",
|
||
"HOTWORDS:Tool,客製化,季會",
|
||
"后处理",
|
||
]
|
||
for marker in required:
|
||
assert marker in text
|