Merge pull request #719 from snakers4/adamnsandle

Adamnsandle

.github/workflows/test.yml

@@ -24,6 +24,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install build hatchling pytest soundfile
+        pip install .[test]
 
     - name: Build package
       run: python -m build --wheel --outdir dist

pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
 name = "silero-vad"
-version = "6.1.0"
+version = "6.2.0"
 authors = [
   {name="Silero Team", email="hello@silero.ai"},
 ]
@@ -37,3 +37,10 @@ dependencies = [
 [project.urls]
 Homepage = "https://github.com/snakers4/silero-vad"
 Issues = "https://github.com/snakers4/silero-vad/issues"
+
+[project.optional-dependencies]
+test = [
+    "pytest",
+    "soundfile",
+    "torch<2.9",
+]

src/silero_vad/utils_vad.py

@@ -223,7 +223,7 @@ def get_speech_timestamps(audio: torch.Tensor,
                           progress_tracking_callback: Callable[[float], None] = None,
                           neg_threshold: float = None,
                           window_size_samples: int = 512,
-                          min_silence_at_max_speech: float = 98,
+                          min_silence_at_max_speech: int = 98,
                           use_max_poss_sil_at_max_speech: bool = True):
 
     """
@@ -272,7 +272,7 @@ def get_speech_timestamps(audio: torch.Tensor,
     neg_threshold: float (default = threshold - 0.15)
         Negative threshold (noise or exit threshold). If model's current state is SPEECH, values BELOW this value are considered as NON-SPEECH.
 
-    min_silence_at_max_speech: float (default - 98ms)
+    min_silence_at_max_speech: int (default - 98ms)
         Minimum silence duration in ms which is used to avoid abrupt cuts when max_speech_duration_s is reached
 
     use_max_poss_sil_at_max_speech: bool (default - True)