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
fix(runtime): release ONNX hotword and timestamp fixes as 0.4.11
zhifu gaod090ceff2d4a
diff --git a/.github/workflows/test-funasr-onnx-package.yml b/.github/workflows/test-funasr-onnx-package.ymlindex 226421da6..18f0b4e54 100644--- a/.github/workflows/test-funasr-onnx-package.yml+++ b/.github/workflows/test-funasr-onnx-package.yml@@ -86,7 +86,7 @@ jobs:import importlib.utilfrom importlib.metadata import requires, version- assert version("funasr-onnx") == "0.4.10"+ assert version("funasr-onnx") == "0.4.11"assert importlib.util.find_spec("torch") is Nonerequirements = requires("funasr-onnx") or []@@ -130,7 +130,7 @@ jobs:if: matrix.python-version == '3.12'uses: actions/upload-artifact@v7with:- name: funasr-onnx-0.4.10+ name: funasr-onnx-0.4.11path: dist/funasr-onnx/*if-no-files-found: errordiff --git a/runtime/python/onnxruntime/README.md b/runtime/python/onnxruntime/README.mdindex e3d18c6d4..4982cc450 100644--- a/runtime/python/onnxruntime/README.md+++ b/runtime/python/onnxruntime/README.md@@ -7,6 +7,12 @@ does not update the installed ONNX wrappers. Check their versions separatelywith `python -m pip show funasr-onnx funasr`; use the source installation belowwhen a required wrapper fix is newer than the published PyPI package.+Version 0.4.11 keeps timestamps independent of padded samples in a batch+(#3871), bounds Contextual/Seaco hotwords to the exported ten-character+embedding input and skips whitespace-only entries (#3882), and preserves+terminal abbreviations and their timestamps (#3869). These are wrapper and+postprocessing fixes, not model-weight updates or ASR accuracy claims.+Version 0.4.10 restores direct librosa decoding for non-WAV audio in offlineand streaming Paraformer, SenseVoice and offline VAD (#3865), without creating a WAV sidecaror treating every non-WAV input as MP3. Codec support still depends on the@@ -45,9 +51,9 @@ and postprocessing fixes, not a model-weight update or an ASR accuracy claim.install from pip```shell-pip install -U "funasr-onnx>=0.4.10"+pip install -U "funasr-onnx>=0.4.11"# For the users in China, you could install with the command:-# pip install -U "funasr-onnx>=0.4.10" -i https://mirror.sjtu.edu.cn/pypi/web/simple+# pip install -U "funasr-onnx>=0.4.11" -i https://mirror.sjtu.edu.cn/pypi/web/simple# If you want to export .onnx file, you should install modelscope and funasrpip install -U modelscope funasr# For the users in China, you could install with the command:diff --git a/runtime/python/onnxruntime/setup.py b/runtime/python/onnxruntime/setup.pyindex 40290072f..22791fa14 100644--- a/runtime/python/onnxruntime/setup.py+++ b/runtime/python/onnxruntime/setup.py@@ -13,7 +13,7 @@ def get_readme():MODULE_NAME = "funasr_onnx"-VERSION_NUM = "0.4.10"+VERSION_NUM = "0.4.11"setuptools.setup(name=MODULE_NAME,diff --git a/tests/test_funasr_onnx_installed.py b/tests/test_funasr_onnx_installed.pyindex b6a74c78e..161870454 100644--- a/tests/test_funasr_onnx_installed.py+++ b/tests/test_funasr_onnx_installed.py@@ -41,6 +41,71 @@ class InstalledOnnxPackageTest(unittest.TestCase):LOADERS = (funasr_onnx.Paraformer, ParaformerOnline,funasr_onnx.SenseVoiceSmall, funasr_onnx.Fsmn_vad)+ def test_long_and_empty_hotwords_stay_within_embedding_bounds(self):+ for cls in (funasr_onnx.ContextualParaformer, funasr_onnx.SeacoParaformer):+ with self.subTest(wrapper=cls.__name__):+ model = cls.__new__(cls)+ model.vocab = {'a': 3, 'b': 4}+ matrix, positions = model.proc_hotword(' ab abababababab ')+ self.assertEqual(matrix.tolist(), [+ [3, 4, 0, 0, 0, 0, 0, 0, 0, 0],+ [3, 4, 3, 4, 3, 4, 3, 4, 3, 4],+ [1, 0, 0, 0, 0, 0, 0, 0, 0, 0],+ ])+ self.assertEqual(positions.tolist(), [1, 9, 0])+ for value in ('', ' \t\n'):+ matrix, positions = model.proc_hotword(value)+ self.assertEqual(matrix.tolist(), [[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]])+ self.assertEqual(positions.tolist(), [0])++ def test_batched_timestamps_use_each_input_length(self):+ def features(lengths):+ return np.zeros((len(lengths), max(lengths), 4), dtype=np.float32), np.array(lengths)++ def acoustic_output(feats, lengths):+ peaks = np.zeros((len(lengths), feats.shape[1] * 3), dtype=np.float32)+ for row, length in enumerate(lengths):+ peaks[row, np.linspace(5, length * 3 - 6, 3).round().astype(int)] = 1+ return None, None, np.zeros_like(peaks), peaks++ # Acoustic outputs are synthetic. The installed batching, timestamp and+ # postprocessing code must keep the shorter sample independent of padding.+ for cls in (funasr_onnx.Paraformer, funasr_onnx.ContextualParaformer,+ funasr_onnx.SeacoParaformer):+ with self.subTest(wrapper=cls.__name__):+ model = cls.__new__(cls)+ model.batch_size = 2+ model.plot_timestamp_to = ''+ model.language = 'zh'+ model.frontend = SimpleNamespace(opts=SimpleNamespace(+ frame_opts=SimpleNamespace(samp_freq=16000)))+ model.load_data = lambda values, fs: values+ model.extract_feat = features+ model.decode = lambda scores, lens: [['\u4f60', '\u597d'] for _ in range(model._rows)]++ def infer(feats, lengths, *unused):+ model._rows = len(lengths)+ return acoustic_output(feats, lengths)++ model.infer = infer+ model.bb_infer = infer+ model.vocab = {'a': 3}+ model.eb_infer = lambda hotwords, lengths: [np.zeros((10, len(hotwords), 4), dtype=np.float32)]+ args = () if cls is funasr_onnx.Paraformer else ('a',)+ single = [model([length], *args)[0] for length in [17, 50]]+ self.assertEqual([x['timestamp'] for x in single], [+ [[70, 470], [470, 945]], [[70, 670], [1450, 2925]],+ ])+ self.assertEqual(model([17, 50], *args), single)++ def test_terminal_abbreviation_preserves_text_and_timestamps(self):+ from funasr_onnx.utils.postprocess_utils import abbr_dispose++ self.assertEqual(abbr_dispose(['a', ' ', 'b']), ['AB'])+ self.assertEqual(abbr_dispose(['a', ' ', 'b'], [[0, 100], [100, 200]]),+ (['AB'], [[0, 200]]))+ self.assertEqual(abbr_dispose(['a', ' ', 'b', ' ', 'c']), ['ABC'])+def test_lossless_non_wav_without_sidecar(self):samples = (np.arange(4800, dtype=np.int16) - 2400).astype(np.float32) / 32768with tempfile.TemporaryDirectory() as directory:@@ -91,7 +156,7 @@ class InstalledOnnxPackageTest(unittest.TestCase):def test_installed_distribution_version_and_origin(self):distribution = importlib.metadata.distribution('funasr-onnx')- self.assertEqual(distribution.version, '0.4.10')+ self.assertEqual(distribution.version, '0.4.11')self.assertEqual(Path(funasr_onnx.__file__).resolve().parent,Path(distribution.locate_file('funasr_onnx')).resolve(),diff --git a/tests/test_funasr_onnx_release.py b/tests/test_funasr_onnx_release.pyindex cb57f6be5..1e73caf87 100644--- a/tests/test_funasr_onnx_release.py+++ b/tests/test_funasr_onnx_release.py@@ -7,7 +7,7 @@ import unittestROOT = Path(__file__).resolve().parents[1]PACKAGE_ROOT = ROOT / "runtime" / "python" / "onnxruntime"SETUP_PATH = PACKAGE_ROOT / "setup.py"-EXPECTED_VERSION = "0.4.10"+EXPECTED_VERSION = "0.4.11"REQUIREMENT_NAME_PATTERN = re.compile(r"^\s*([A-Za-z0-9](?:[A-Za-z0-9._-]*[A-Za-z0-9])?)")@@ -44,7 +44,7 @@ def normalized_requirement_name(requirement):class FunASROnnxReleaseContractTest(unittest.TestCase):- def test_release_version_is_0_4_10(self):+ def test_release_version_is_0_4_11(self):self.assertEqual(assigned_literal(read_setup_tree(), "VERSION_NUM"), EXPECTED_VERSION)def test_standalone_license_preserves_repository_notice(self):@@ -83,6 +83,9 @@ class FunASROnnxReleaseContractTest(unittest.TestCase):self.assertIn("#3847", readme)self.assertIn("empty or sub-frame", readme)self.assertIn("preserves the streaming cache", readme)+ self.assertIn("#3869", readme)+ self.assertIn("#3871", readme)+ self.assertIn("#3882", readme)def test_runtime_dependencies_keep_onnx_install_torch_free(self):requirements = setup_keyword_literal(read_setup_tree(), "install_requires")