mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-05 04:24:39 -04:00
Stefan Walcz
985df46d24
AudioTranscription caught every exception and returned an empty TranscriptResult. A failed diarization step therefore discarded a transcript that was already finished: with an HF token that has not accepted the terms of the gated pyannote pipeline, the download fails with 403 and every transcription came back as an empty text with HTTP 200. Diarization now degrades: if it fails, the transcript is returned without speaker labels and the reason is logged. Any other failure aborts the call with INTERNAL instead of pretending success with an empty text. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>
44 lines
1.4 KiB
Python
44 lines
1.4 KiB
Python
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,
|
|
)
|
|
|
|
|
|
def test_failed_diarization_keeps_the_transcript(self):
|
|
transcript = {"segments": [{"text": "Die Rechnung"}]}
|
|
logged = []
|
|
|
|
def refused(_):
|
|
raise RuntimeError("403 Client Error: gated repo")
|
|
|
|
result = transcript_utils.diarize_or_keep(transcript, refused, logged.append)
|
|
self.assertIs(result, transcript)
|
|
self.assertIn("403", logged[0])
|
|
|
|
def test_successful_diarization_is_returned(self):
|
|
transcript = {"segments": [{"text": "Die Rechnung"}]}
|
|
with_speakers = {"segments": [{"text": "Die Rechnung", "speaker": "SPEAKER_00"}]}
|
|
result = transcript_utils.diarize_or_keep(transcript, lambda _: with_speakers, lambda _: None)
|
|
self.assertIs(result, with_speakers)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|