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 non-WAV audio loading as 0.4.10
zhifu gaoc10d8bd118cc
diff --git a/.github/workflows/test-funasr-onnx-package.yml b/.github/workflows/test-funasr-onnx-package.ymlindex f94b86e09..226421da6 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") == "0.4.9"+ assert version("funasr-onnx") == "0.4.10"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-0.4.9+ name: funasr-onnx-0.4.10path: dist/funasr-onnx/*if-no-files-found: errordiff --git a/runtime/python/onnxruntime/README.md b/runtime/python/onnxruntime/README.mdindex 8794ac4c7..e3d18c6d4 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 0.4.10 restores direct librosa decoding for non-WAV audio in offline+and streaming Paraformer, SenseVoice and offline VAD (#3865), without creating a WAV sidecar+or treating every non-WAV input as MP3. Codec support still depends on the+installed audio backend. This is a runtime loading fix, not a model-weight+or ASR accuracy update.+Version 0.4.9 keeps one result per input when offline VAD receives empty or sub-frameaudio, without invoking ONNX Runtime for zero-frame features (#3846). It also returnsan empty punctuation chunk while it preserves the streaming cache and avoids@@ -39,9 +45,9 @@ and postprocessing fixes, not a model-weight update or an ASR accuracy claim.install from pip```shell-pip install -U "funasr-onnx>=0.4.9"+pip install -U "funasr-onnx>=0.4.10"# For the users in China, you could install with the command:-# pip install -U "funasr-onnx>=0.4.9" -i https://mirror.sjtu.edu.cn/pypi/web/simple+# pip install -U "funasr-onnx>=0.4.10" -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 b5236ffc1..40290072f 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 = "0.4.9"+VERSION_NUM = "0.4.10"setuptools.setup(name=MODULE_NAME,diff --git a/tests/test_funasr_onnx_installed.py b/tests/test_funasr_onnx_installed.pyindex 4b3c254ee..b6a74c78e 100644--- a/tests/test_funasr_onnx_installed.py+++ b/tests/test_funasr_onnx_installed.py@@ -19,6 +19,8 @@ if importlib.util.find_spec('funasr_onnx') is None:raise unittest.SkipTest('Install the standalone funasr-onnx distribution first.')import funasr_onnx+import numpy as np+import soundfile as sffrom funasr_onnx.paraformer_online_bin import Paraformer as ParaformerOnline@@ -36,9 +38,60 @@ ENTRYPOINTS = (class InstalledOnnxPackageTest(unittest.TestCase):+ LOADERS = (funasr_onnx.Paraformer, ParaformerOnline,+ funasr_onnx.SenseVoiceSmall, funasr_onnx.Fsmn_vad)++ def test_lossless_non_wav_without_sidecar(self):+ samples = (np.arange(4800, dtype=np.int16) - 2400).astype(np.float32) / 32768+ with tempfile.TemporaryDirectory() as directory:+ path = Path(directory) / 'sample.flac'+ sf.write(path, samples, 16000, subtype='PCM_16')+ before = path.read_bytes()+ for cls in self.LOADERS:+ with self.subTest(loader=cls.__module__):+ result = cls.__new__(cls).load_data(str(path), fs=16000)+ self.assertEqual(len(result), 1)+ np.testing.assert_array_equal(result[0], samples)+ self.assertEqual(path.read_bytes(), before)+ self.assertEqual(sorted(p.name for p in path.parent.iterdir()), ['sample.flac'])++ def test_wav_and_flac_list_preserves_input_order(self):+ first = np.full(800, 0.125, dtype=np.float32)+ second = np.full(1200, -0.25, dtype=np.float32)+ with tempfile.TemporaryDirectory() as directory:+ paths = [Path(directory) / 'first.wav', Path(directory) / 'second.flac']+ for path, samples in zip(paths, [first, second]):+ sf.write(path, samples, 16000, subtype='PCM_16')+ for cls in self.LOADERS:+ with self.subTest(loader=cls.__module__):+ result = cls.__new__(cls).load_data([str(p) for p in paths], fs=16000)+ self.assertEqual(len(result), 2)+ np.testing.assert_array_equal(result[0], first)+ np.testing.assert_array_equal(result[1], second)+ self.assertEqual(sorted(p.name for p in Path(directory).iterdir()), ['first.wav', 'second.flac'])++ def test_waveform_array_is_preserved(self):+ samples = np.linspace(-0.25, 0.25, 320, dtype=np.float32)+ for cls in self.LOADERS:+ with self.subTest(loader=cls.__module__):+ result = cls.__new__(cls).load_data(samples, fs=16000)+ self.assertEqual(len(result), 1)+ self.assertIs(result[0], samples)++ def test_invalid_audio_remains_visible_without_sidecar(self):+ with tempfile.TemporaryDirectory() as directory:+ path = Path(directory) / 'invalid.flac'+ path.write_bytes(b'not audio')+ for cls in self.LOADERS:+ with self.subTest(loader=cls.__module__):+ with self.assertRaises(Exception):+ cls.__new__(cls).load_data(str(path), fs=16000)+ self.assertEqual(path.read_bytes(), b'not audio')+ self.assertEqual(sorted(p.name for p in path.parent.iterdir()), ['invalid.flac'])+def test_installed_distribution_version_and_origin(self):distribution = importlib.metadata.distribution('funasr-onnx')- self.assertEqual(distribution.version, '0.4.9')+ self.assertEqual(distribution.version, '0.4.10')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 160c24aa4..cb57f6be5 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 = "0.4.9"+EXPECTED_VERSION = "0.4.10"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_9(self):+ def test_release_version_is_0_4_10(self):self.assertEqual(assigned_literal(read_setup_tree(), "VERSION_NUM"), EXPECTED_VERSION)def test_standalone_license_preserves_repository_notice(self):@@ -68,6 +68,8 @@ class FunASROnnxReleaseContractTest(unittest.TestCase):readme = (PACKAGE_ROOT / "README.md").read_text()self.assertIn(f'pip install -U "funasr-onnx>={EXPECTED_VERSION}"', readme)self.assertIn("does not update the installed ONNX wrappers", readme)+ self.assertIn("#3865", readme)+ self.assertIn("without creating a WAV sidecar", readme)self.assertIn("short/final VAD", readme)self.assertIn("zero-overlap", readme)self.assertIn("one independent result per input", readme)