Updated configuration to utilize segment ids provided in the input transcript
This commit is contained in:
@@ -12,7 +12,7 @@ class CountEstimator:
|
||||
|
||||
def _segments(count):
|
||||
payload = [
|
||||
{"speaker": "Eric", "start": float(i), "end": float(i + 1), "text": f"Segment {i}"}
|
||||
{"id": i + 1, "speaker": "Eric", "start": float(i), "end": float(i + 1), "text": f"Segment {i}"}
|
||||
for i in range(count)
|
||||
]
|
||||
import json
|
||||
@@ -37,4 +37,3 @@ def test_chunk_transcript_allows_exact_limit():
|
||||
def test_chunk_transcript_rejects_oversized_single_segment():
|
||||
with pytest.raises(AuditaValidationError):
|
||||
chunk_transcript(_segments(1), max_section_tokens=9, estimator=CountEstimator())
|
||||
|
||||
|
||||
Reference in New Issue
Block a user