branderson
2debfb171c
Also fix a secondary ripple in build_notes(): a skipped row (inside a missing span) no longer advances prev_line/prev_end, so it can't corrupt line-initial spacing or break timing for its own line's later words.
67 lines
3.1 KiB
Python
67 lines
3.1 KiB
Python
from songtrace.lyrics import normalize_lyrics
|
|
from songtrace.whisper_client import TranscriptSegment
|
|
from songtrace.stages.transcribe import classify_lyrics_match, lyrics_similarity, vocal_sections
|
|
|
|
def seg(s, e, t=""):
|
|
return TranscriptSegment(start=s, end=e, text=t)
|
|
|
|
def test_vocal_sections_merges_close_segments():
|
|
sections = vocal_sections([seg(2, 5), seg(6, 9), seg(30, 33)])
|
|
assert sections == [(1.0, 10.0), (29.0, 34.0)]
|
|
|
|
def test_vocal_sections_handles_out_of_order_segments():
|
|
sections = vocal_sections([seg(30, 33), seg(1, 4)])
|
|
assert sections == [(0.0, 5.0), (29.0, 34.0)]
|
|
|
|
def test_vocal_sections_keeps_contained_segment():
|
|
sections = vocal_sections([seg(1, 10), seg(3, 5)])
|
|
assert sections == [(0.0, 11.0)]
|
|
|
|
def test_similarity_high_for_matching_lyrics():
|
|
ref = normalize_lyrics("it's one two three\nfour five six seven eight")
|
|
segs = [seg(0, 2, "It's one two three"), seg(2, 4, "four five six seven eight")]
|
|
assert lyrics_similarity(segs, ref) > 0.9
|
|
|
|
def test_similarity_low_for_wrong_lyrics():
|
|
ref = normalize_lyrics("completely different words here entirely")
|
|
segs = [seg(0, 2, "it's one two three four five six seven eight")]
|
|
assert lyrics_similarity(segs, ref) < 0.4
|
|
|
|
def test_classify_lyrics_match_flags_extra_reference_line():
|
|
ref = normalize_lyrics("it's one two three\nfour five six seven eight\nnine ten eleven")
|
|
segs = [seg(1, 4, "it's one two three four five six seven eight")]
|
|
dropped, missing = classify_lyrics_match(segs, ref)
|
|
assert dropped == [2]
|
|
assert missing == []
|
|
|
|
def test_classify_lyrics_match_flags_unmatched_singing():
|
|
ref = normalize_lyrics("it's one two three\nfour five six seven eight")
|
|
segs = [seg(1, 4, "it's one two three four five six seven eight"),
|
|
seg(20, 23, "completely unrelated ad lib bridge")]
|
|
dropped, missing = classify_lyrics_match(segs, ref)
|
|
assert dropped == []
|
|
assert missing == [(19.0, 24.0)]
|
|
|
|
def test_classify_lyrics_match_keeps_partially_matched_lines():
|
|
ref = normalize_lyrics("it's one two three\nfour five six seven eight")
|
|
# line 1 heard with one word garbled ("five" -> "fife"): still a replace/equal
|
|
# match, so the line stays matched rather than dropped
|
|
segs = [seg(1, 4, "it's one two three four fife six seven eight")]
|
|
dropped, _ = classify_lyrics_match(segs, ref)
|
|
assert dropped == []
|
|
|
|
def test_classify_lyrics_match_scopes_missing_span_to_adlib_not_whole_section():
|
|
# matched line and an unmatched ad-lib close enough together that
|
|
# vocal_sections would merge them into one section; missing_spans must
|
|
# stay tight around the ad-lib so the matched line keeps its notes.
|
|
ref = normalize_lyrics("it's one two three\nfour five six seven eight")
|
|
segs = [seg(1, 4, "it's one two three four five six seven eight"),
|
|
seg(6, 8, "completely unrelated ad lib")]
|
|
sections = vocal_sections(segs)
|
|
assert sections == [(0.0, 9.0)] # confirms the two segments do merge
|
|
dropped, missing = classify_lyrics_match(segs, ref)
|
|
assert dropped == []
|
|
assert missing == [(5.0, 9.0)]
|
|
for a, b in missing:
|
|
assert not (a <= 1.0 < b) # matched line's start (1.0) untouched
|