branderson
62b6c891c8
A line with nothing in the transcript was always dropped as not sung. When Whisper skips a passage (one song lost a whole verse, 50s of clear singing with no segments), that drops lines that were sung. Find singing in the vocal stem that no segment covers; a run of unmatched lines with such singing between its heard neighbours is kept, and that singing joins the alignment sections so those lines have somewhere to go. Only singing that kept a line is added, so an untranscribed ad-lib draws no lines into it.
96 lines
4.4 KiB
Python
96 lines
4.4 KiB
Python
from songtrace.lyrics import normalize_lyrics
|
|
from songtrace.whisper_client import TranscriptSegment
|
|
from songtrace.stages.transcribe import (classify_lyrics_match, lyrics_similarity,
|
|
recovered_spans, 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 review marks the right place.
|
|
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
|
|
|
|
|
|
THREE_LINES = "one two three\nfour five six\nseven eight nine"
|
|
|
|
|
|
def test_lines_whisper_missed_are_kept_when_singing_went_untranscribed():
|
|
ref = normalize_lyrics(THREE_LINES)
|
|
segs = [seg(0, 2, "one two three"), seg(20, 22, "seven eight nine")]
|
|
assert classify_lyrics_match(segs, ref)[0] == [1]
|
|
dropped, _ = classify_lyrics_match(segs, ref, unheard=[(8.0, 14.0)])
|
|
assert dropped == []
|
|
|
|
|
|
def test_untranscribed_singing_elsewhere_does_not_keep_a_line():
|
|
ref = normalize_lyrics(THREE_LINES)
|
|
segs = [seg(0, 2, "one two three"), seg(20, 22, "seven eight nine")]
|
|
dropped, _ = classify_lyrics_match(segs, ref, unheard=[(30.0, 35.0)])
|
|
assert dropped == [1]
|
|
|
|
|
|
def test_recovered_spans_are_the_singing_between_heard_neighbours():
|
|
ref = normalize_lyrics(THREE_LINES)
|
|
segs = [seg(10, 12, "four five six"), seg(20, 22, "seven eight nine")]
|
|
unheard = [(3.0, 9.0), (14.0, 18.0), (30.0, 35.0)]
|
|
# line 0 comes before anything heard, so only the singing before line 1
|
|
# can stand in for it; the other spans have no missing line around them
|
|
assert recovered_spans(segs, ref, unheard) == [(3.0, 9.0)]
|
|
assert classify_lyrics_match(segs, ref, unheard=unheard)[0] == []
|