fix(whisperx): reject unconfigured diarization

WhisperX silently returned a plain transcript when diarization lacked
the Hugging Face token required to load pyannote. Reject that request
clearly so callers do not mistake missing speaker labels for a
successful diarization.

Convert WhisperX seconds to the nanosecond duration unit used by the
transcription API.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/python/whisperx/backend.py

@@ -16,6 +16,7 @@ import grpc
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
 from grpc_auth import get_auth_interceptors
+from transcript_utils import require_diarization_token, seconds_to_nanoseconds
 
 
 
@@ -81,6 +82,11 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         import whisperx
         from whisperx.diarize import DiarizationPipeline
 
+        try:
+            require_diarization_token(request.diarize, self.hf_token)
+        except ValueError as err:
+            context.abort(grpc.StatusCode.FAILED_PRECONDITION, str(err))
+
         resultSegments = []
         text = ""
         try:
@@ -117,8 +123,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             # Build result segments
             for idx, seg in enumerate(transcript["segments"]):
                 seg_text = seg.get("text", "")
-                start = int(seg.get("start", 0))
-                end = int(seg.get("end", 0))
+                start = seconds_to_nanoseconds(seg.get("start", 0))
+                end = seconds_to_nanoseconds(seg.get("end", 0))
                 speaker = seg.get("speaker", "")
 
                 resultSegments.append(backend_pb2.TranscriptSegment(

backend/python/whisperx/test_transcript_utils.py

@@ -0,0 +1,25 @@
+import unittest
+
+import transcript_utils
+
+
+class TestTranscriptUtils(unittest.TestCase):
+    def test_diarization_requires_hugging_face_token(self):
+        with self.assertRaisesRegex(
+            ValueError,
+            "HF_TOKEN is required for WhisperX diarization",
+        ):
+            transcript_utils.require_diarization_token(True, None)
+
+    def test_diarization_does_not_require_token_when_disabled(self):
+        transcript_utils.require_diarization_token(False, None)
+
+    def test_seconds_are_serialized_as_nanoseconds(self):
+        self.assertEqual(
+            transcript_utils.seconds_to_nanoseconds(3.25),
+            3_250_000_000,
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()

backend/python/whisperx/transcript_utils.py

@@ -0,0 +1,12 @@
+"""Helpers for WhisperX transcript responses."""
+
+
+def require_diarization_token(diarize, token):
+    """Reject diarization when WhisperX cannot load its gated pipeline."""
+    if diarize and not token:
+        raise ValueError("HF_TOKEN is required for WhisperX diarization")
+
+
+def seconds_to_nanoseconds(seconds):
+    """Convert WhisperX timestamps to the duration unit used by LocalAI."""
+    return int(seconds * 1_000_000_000)