Skip to content

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

Use QwenAudio canonical repository links (#192)

zhifu gaofbdca8689bb8
diff --git a/README.md b/README.md
index 69f8d86..235cfa3 100644
--- a/README.md
+++ b/README.md
@@ -193,9 +193,9 @@ FunClip is part of the **FunAudioLLM** family:
| Project | Description | Stars |
|---------|-------------|-------|
| [FunASR](https://github.com/modelscope/FunASR) | Industrial speech recognition toolkit — VAD, ASR, punctuation, diarization | [![](https://img.shields.io/github/stars/modelscope/FunASR?style=social)](https://github.com/modelscope/FunASR) |
-| [Fun-ASR-Nano](https://github.com/FunAudioLLM/Fun-ASR) | End-to-end LLM-based ASR — flagship and separate 31-language MLT checkpoints, streaming, hotwords ([HF model](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | [![](https://img.shields.io/github/stars/FunAudioLLM/Fun-ASR?style=social)](https://github.com/FunAudioLLM/Fun-ASR) |
-| [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) | Multilingual speech understanding — ASR + emotion + audio events ([HF model](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)) | [![](https://img.shields.io/github/stars/FunAudioLLM/SenseVoice?style=social)](https://github.com/FunAudioLLM/SenseVoice) |
-| [CosyVoice](https://github.com/FunAudioLLM/CosyVoice) | Natural speech generation — multi-language, zero-shot cloning | [![](https://img.shields.io/github/stars/FunAudioLLM/CosyVoice?style=social)](https://github.com/FunAudioLLM/CosyVoice) |
+| [Fun-ASR-Nano](https://github.com/QwenAudio/Fun-ASR) | End-to-end LLM-based ASR — flagship and separate 31-language MLT checkpoints, streaming, hotwords ([HF model](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | [![](https://img.shields.io/github/stars/QwenAudio/Fun-ASR?style=social)](https://github.com/QwenAudio/Fun-ASR) |
+| [SenseVoice](https://github.com/QwenAudio/SenseVoice) | Multilingual speech understanding — ASR + emotion + audio events ([HF model](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)) | [![](https://img.shields.io/github/stars/QwenAudio/SenseVoice?style=social)](https://github.com/QwenAudio/SenseVoice) |
+| [CosyVoice](https://github.com/QwenAudio/CosyVoice) | Natural speech generation — multi-language, zero-shot cloning | [![](https://img.shields.io/github/stars/QwenAudio/CosyVoice?style=social)](https://github.com/QwenAudio/CosyVoice) |
📚FunASR Paper: <a href="https://arxiv.org/abs/2305.11013"><img src="https://img.shields.io/badge/Arxiv-2305.11013-orange"></a>
📚SeACo-Paraformer Paper: <a href="https://arxiv.org/abs/2308.03266"><img src="https://img.shields.io/badge/Arxiv-2308.03266-orange"></a>
diff --git a/funclip/introduction.py b/funclip/introduction.py
index cf08652..a6b0c50 100644
--- a/funclip/introduction.py
+++ b/funclip/introduction.py
@@ -6,7 +6,7 @@ top_md_1 = ("""
</div>
</div>
- 基于阿里巴巴通义实验室自研并开源的[FunASR](https://github.com/modelscope/FunASR)工具包及Paraformer、[Fun-ASR-Nano](https://github.com/FunAudioLLM/Fun-ASR)、[SenseVoice](https://github.com/FunAudioLLM/SenseVoice)系列模型及语音识别、端点检测、标点预测、时间戳预测、说话人区分、热词定制化开源链路
+ 基于阿里巴巴通义实验室自研并开源的[FunASR](https://github.com/modelscope/FunASR)工具包及Paraformer、[Fun-ASR-Nano](https://github.com/QwenAudio/Fun-ASR)、[SenseVoice](https://github.com/QwenAudio/SenseVoice)系列模型及语音识别、端点检测、标点预测、时间戳预测、说话人区分、热词定制化开源链路
准确识别,自由复制所需段落,或者设置说话人标识,一键裁剪、添加字幕
diff --git a/tests/test_canonical_qwenaudio_links.py b/tests/test_canonical_qwenaudio_links.py
new file mode 100644
index 0000000..f6b0a88
--- /dev/null
+++ b/tests/test_canonical_qwenaudio_links.py
@@ -0,0 +1,74 @@
+import re
+import subprocess
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+LEGACY_GITHUB_REPO = re.compile(
+ r"FunAudioLLM/(?:CosyVoice|Fun-ASR|SenseVoice)(?![A-Za-z0-9_-])"
+)
+LEGACY_GITHUB_OWNER_URL = re.compile(
+ r"https://(?:github\.com|img\.shields\.io/github/stars)/FunAudioLLM/"
+)
+HUGGING_FACE_URL = re.compile(
+ r"https://huggingface\.co/(?:spaces/)?FunAudioLLM/[^\s)>'\"]+"
+)
+
+
+def _tracked_text_files():
+ result = subprocess.run(
+ ["git", "ls-files", "-z"],
+ cwd=ROOT,
+ check=True,
+ capture_output=True,
+ )
+ for raw_path in result.stdout.split(b"\0"):
+ if not raw_path:
+ continue
+ path = ROOT / raw_path.decode()
+ try:
+ yield path, path.read_text(encoding="utf-8")
+ except (FileNotFoundError, UnicodeDecodeError, IsADirectoryError):
+ continue
+
+
+def test_legacy_owner_matcher_covers_repository_api_and_charts():
+ legacy_examples = (
+ "https://api.github.com/repos/FunAudioLLM/CosyVoice",
+ "https://api.star-history.com/svg?repos=FunAudioLLM/CosyVoice&type=Date",
+ "https://github.com/FunAudioLLM/CosyVoice",
+ "https://img.shields.io/github/stars/FunAudioLLM/CosyVoice",
+ "FunAudioLLM/Fun-ASR",
+ "FunAudioLLM/SenseVoice",
+ )
+ for text in legacy_examples:
+ without_hugging_face_urls = HUGGING_FACE_URL.sub("", text)
+ assert LEGACY_GITHUB_OWNER_URL.search(text) or LEGACY_GITHUB_REPO.search(
+ without_hugging_face_urls
+ )
+
+ allowed_examples = (
+ "https://huggingface.co/FunAudioLLM/CosyVoice",
+ "https://huggingface.co/spaces/FunAudioLLM/SenseVoice",
+ "FunAudioLLM/CosyVoice-300M",
+ "FunAudioLLM/Fun-ASR-Nano-2512",
+ "FunAudioLLM/SenseVoiceSmall",
+ )
+ for text in allowed_examples:
+ without_hugging_face_urls = HUGGING_FACE_URL.sub("", text)
+ assert not LEGACY_GITHUB_OWNER_URL.search(text)
+ assert not LEGACY_GITHUB_REPO.search(without_hugging_face_urls)
+
+
+def test_tracked_files_use_qwenaudio_for_canonical_github_repositories():
+ offenders = []
+ for path, text in _tracked_text_files():
+ if path.resolve() == Path(__file__).resolve():
+ continue
+ without_hugging_face_urls = HUGGING_FACE_URL.sub("", text)
+ if LEGACY_GITHUB_OWNER_URL.search(text) or LEGACY_GITHUB_REPO.search(
+ without_hugging_face_urls
+ ):
+ offenders.append(str(path.relative_to(ROOT)))
+
+ assert not offenders, "legacy GitHub repository owner in: " + ", ".join(offenders)
diff --git a/tests/test_funasr_requirement.py b/tests/test_funasr_requirement.py
index 6e9cc39..29a6988 100644
--- a/tests/test_funasr_requirement.py
+++ b/tests/test_funasr_requirement.py
@@ -6,16 +6,18 @@ ROOT = Path(__file__).resolve().parents[1]
def test_funasr_minimum_version_matches_current_model_paths():
requirements = (ROOT / "requirements.txt").read_text()
- assert "funasr>=1.3.27" in requirements
+ assert "funasr>=1.3.28" in requirements
assert "funasr>=1.1.2" not in requirements
assert "funasr>=1.3.26" not in requirements
+ assert "funasr>=1.3.27" not in requirements
def test_readmes_explain_upgrade_for_existing_installs():
for readme in ["README.md", "README_zh.md"]:
text = (ROOT / readme).read_text()
- assert 'pip install -U "funasr>=1.3.27"' in text
+ assert 'pip install -U "funasr>=1.3.28"' in text
assert "funasr>=1.3.26" not in text
+ assert "funasr>=1.3.27" not in text
def test_readmes_route_edge_asr_users_to_gguf_runtime():