eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Updated configuration to utilize segment ids provided in the input transcript

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-21 15:01:31 -05:00
parent 7e1a3f721a
commit ca01e46d77
13 changed files with 186 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/test_prompts.py
View File

@@ -9,7 +9,7 @@ def test_prompt_requires_acoustically_plausible_transcription_errors():
transcript = parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 0.0, "end": 1.0, "text": "The gestures are nearby."}
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "The gestures are nearby."}
]
"""
)
@@ -43,7 +43,7 @@ def test_prompt_uses_simplified_segment_payload():
transcript = parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 0.0, "end": 1.0, "text": "The gestures are nearby."}
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "The gestures are nearby."}
]
"""
)
@@ -61,7 +61,7 @@ def test_prompt_uses_simplified_segment_payload():
transcript_json = messages[1]["content"].split("Transcript section:\n", maxsplit=1)[1]
prompt_segments = json.loads(transcript_json)
assert prompt_segments == [{"segment_id": 0, "original_text": "The gestures are nearby."}]
assert prompt_segments == [{"id": 1, "original_text": "The gestures are nearby."}]
assert "speaker" not in prompt_segments[0]
assert "start" not in prompt_segments[0]
assert "end" not in prompt_segments[0]