Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -739,7 +739,7 @@ def _process_stream_event(self, data: dict) -> None:
words = data.get("words", [])
start_time = words[0].get("start", 0) if words else 0
end_time = words[-1].get("end", 0) if words else 0
language_code = data.get("language_code", self._language)
language_code = data.get("language_code") or self._language

normalized_language = LanguageCode(language_code) if language_code else LanguageCode("en")

Expand Down
40 changes: 40 additions & 0 deletions tests/test_plugin_elevenlabs_stt.py
Original file line number Diff line number Diff line change
Expand Up @@ -501,6 +501,46 @@ def test_final_transcript_keeps_the_plain_copy_without_detection() -> None:
assert finals[0].alternatives[0].language == "es"


@pytest.mark.parametrize(
"message_type",
["partial_transcript", "committed_transcript", "committed_transcript_with_timestamps"],
)
@pytest.mark.parametrize(
("language", "language_data", "expected_language"),
[
("es", {}, "es"),
("es", {"language_code": None}, "es"),
("es", {"language_code": ""}, "es"),
("es", {"language_code": "fra"}, "fr"),
(None, {}, "en"),
(None, {"language_code": None}, "en"),
(None, {"language_code": ""}, "en"),
(None, {"language_code": "fra"}, "fr"),
],
)
def test_transcript_language_falls_back_to_configured_language(
message_type: str,
language: str | None,
language_data: dict[str, str | None],
expected_language: str,
) -> None:
stream = _new_stream(
language=language,
include_timestamps=message_type == "committed_transcript_with_timestamps",
include_language_detection=False,
)

stream._process_stream_event({"message_type": message_type, "text": "hola", **language_data})

transcript = stream._event_ch.events[-1]
assert transcript.type == (
stt.SpeechEventType.INTERIM_TRANSCRIPT
if message_type == "partial_transcript"
else stt.SpeechEventType.FINAL_TRANSCRIPT
)
assert transcript.alternatives[0].language == expected_language


class _FakeWS:
"""Records outgoing messages. receive() parks so recv_task stays alive."""

Expand Down
Loading