Upload 2 files

speaker_diarization.py

@@ -0,0 +1,12 @@
+from pyannote.audio import Pipeline
+import os
+
+hf_token = os.environ.get("HF_TOKEN")
+
+diarization_pipeline = Pipeline.from_pretrained(
+      "pyannote/speaker-diarization-3.1",
+    use_auth_token=hf_token
+)
+
+def diarize_speakers(audio_path):
+    return diarization_pipeline(audio_path)

vad_segmentation.py

@@ -0,0 +1,19 @@
+import os
+from pyannote.audio import Model
+from pyannote.audio.pipelines import VoiceActivityDetection
+hf_token = os.environ.get("HF_TOKEN")
+
+model = Model.from_pretrained("pyannote/segmentation", 
+                              use_auth_token=hf_token)
+
+
+vad_pipeline = VoiceActivityDetection(segmentation=model)
+HYPER_PARAMETERS = {
+  "onset": 0.5, "offset": 0.5,
+  "min_duration_on": 0.0,
+  "min_duration_off": 0.0
+}
+
+vad_pipeline.instantiate(HYPER_PARAMETERS)
+def vad_segmentation(input_path, output_path, aggressiveness=2):
+    return vad_pipeline(input_path)