markers.find_intro_end_via_synopsis sequence-aligns the ASR transcript against metadata.synopsis_text()'s deterministic reconstruction of the expected per-episode announcement text (the say.php reproduction from earlier), rather than matching against a fixed phrase list. This was a direct response to the pattern across the last several fixes: each one patched a single new mis-hearing variant, with no ceiling on how many exist. Sequence alignment tolerates scattered word-level ASR errors throughout the transcript, not just at phrase boundaries someone thought to special-case. Applied to both the official-SRT and ASR-anchor paths (_resolve_intro_end in detect.py), since wording drift and ASR mis-hearings affect both. Falls back to the existing fixed-phrase matching when there's no expected text to align against, and still defers to it entirely for the sponsor-ad-read continuation, which has no deterministic per-episode text of its own. Live-verified: hpr2157 moved from 15.1s (old marker match) to 30.6s; hpr3237 to 34.7s; hpr3009 (Linux Inlaws) extended further but stayed correctly flagged rather than silently trusted; hpr4775 now resolves via official_srt+synopsis_alignment+reference_xcorr_floor, composing all three recent fixes. hpr1892 correctly still returns None -- its garbling is concentrated in the first ~17 words, with no confident anchor near the start, which the leading-anchor check is specifically designed to catch rather than trust a coincidental later match. Also fixes a real bug found while validating this: the sponsor-ad-read continuation was filtering segments by end time instead of start time, so a segment that merely ended near the anchor but started before it broke the extension chain immediately, discarding a real extension (caught on hpr2157's own sponsor read). New test file test_synopsis_alignment.py (8 tests), plus two tests locking in the earlier narrowly-scoped fuzzy-threshold exception for the station-name marker (validated against both the real mis-hearing and the original hpr0500 regression case before being enabled).
124 lines
6.8 KiB
Python
124 lines
6.8 KiB
Python
"""
|
|
Tests for markers.find_intro_end_via_synopsis -- sequence-alignment
|
|
against the deterministically-known expected TTS text, rather than a
|
|
fixed phrase list. See markers.py's docstring for why this exists.
|
|
"""
|
|
import unittest
|
|
|
|
from hpr_stripper import markers
|
|
|
|
|
|
class TestSynopsisAlignment(unittest.TestCase):
|
|
def test_scattered_garbling_throughout_still_aligns(self):
|
|
# hpr2157, real metadata (metadata.synopsis_text) and real
|
|
# Whisper tiny transcription. The title, host name, and series
|
|
# fields are each garbled *differently* from the real text
|
|
# ("Markham Manchester" for "BarCamp Manchester", "Tony H1,212"
|
|
# for "TonyH1 2 1 2") -- no single phrase marker, literal or
|
|
# fuzzy, could reconstruct this. But the surrounding boilerplate
|
|
# words still align, giving enough confirmed evidence overall.
|
|
expected = (
|
|
'This is Hacker Public Radio episode 2157 for Tuesday the 8 of November 2016. '
|
|
'Todays show is entitled. BarCamp Manchester part 3. It is part of the series '
|
|
'"Interviews". It is the 60th show of Tony Hughes A.K.A TonyH1 2 1 2, and is '
|
|
'about 8 minutes long. It carries a clean flag. . The summary is. This is an '
|
|
"interview with Alan O'Donohoe which I did at BarCamp Manchester."
|
|
)
|
|
segments = [
|
|
("This in HPR episode 2,157 entitled Markham Manchester Part 3, and in part of the series, Interviews.", 0.0, 8.1),
|
|
("It is posted by Tony H1,212, and in about 8 minutes long.", 8.1, 14.0),
|
|
("The summary is.", 14.0, 15.1),
|
|
("This in an Interview with Alononovo, which I did at Markham Manchester.", 15.1, 19.8),
|
|
]
|
|
result = markers.find_intro_end_via_synopsis(segments, expected)
|
|
self.assertEqual(result, 19.8)
|
|
|
|
def test_garbling_concentrated_at_the_start_correctly_declines(self):
|
|
# hpr1892, real metadata and real Whisper tiny transcription: "This
|
|
# image PR episode" (garbling "This is HPR episode") plus a wrong
|
|
# host name and episode number leaves no confident match anywhere
|
|
# near the start of the clip. Unlike hpr2157, there's no early
|
|
# anchor to bridge from -- correctly returns None rather than
|
|
# trusting a match that only appears deep into the transcript
|
|
# (leading_anchor_words). This is an accepted limitation, not a
|
|
# bug: some transcripts are too degraded for any method to
|
|
# safely resolve.
|
|
expected = (
|
|
'This is Hacker Public Radio episode 1892 for Tuesday the 3 of November 2015. '
|
|
'Todays show is entitled. my chicken coop. It is part of the series '
|
|
'"Hobby Electronics". It is hosted by Jezra, and is about 10 minutes long. '
|
|
'It carries an explicit flag. . The summary is. '
|
|
'jezra blabs about the brok brok brok house'
|
|
)
|
|
segments = [
|
|
("This image PR episode £1,802 entitled Magic in Cube.", 0.0, 5.2),
|
|
("It is posted by General and in about 10 minutes long.", 5.2, 8.4),
|
|
("The summary is, General Blam about the Brock Brock House.", 8.4, 12.3),
|
|
]
|
|
self.assertIsNone(markers.find_intro_end_via_synopsis(segments, expected))
|
|
|
|
def test_sponsor_ad_read_is_appended_after_the_synopsis_anchor(self):
|
|
# hpr2263-style: once the per-episode synopsis is confirmed by
|
|
# alignment, a following sponsor ad-read (no deterministic
|
|
# per-episode text of its own) should still extend the boundary
|
|
# via the existing marker list, not get dropped on the floor.
|
|
expected = (
|
|
"This is Hacker Public Radio episode 2263 for Monday the 1st of January 2018. "
|
|
"Todays show is entitled. Test Episode. It is hosted by Test Host, and is about "
|
|
"5 minutes long. It carries a clean flag. The summary is. A short test episode."
|
|
)
|
|
segments = [
|
|
("This is Hacker Public Radio episode 2263 for Monday the 1st of January 2018.", 0.0, 8.0),
|
|
("Todays show is entitled. Test Episode.", 8.0, 10.0),
|
|
("It is hosted by Test Host, and is about 5 minutes long.", 10.0, 14.0),
|
|
("It carries a clean flag.", 14.0, 16.0),
|
|
("The summary is. A short test episode.", 16.0, 19.0),
|
|
("This episode of HPR is brought to you by An Honest Host.com.", 19.0, 23.0),
|
|
("Get 15% discount on all shared hosting, with the offer code HPR15.", 23.0, 28.0),
|
|
]
|
|
result = markers.find_intro_end_via_synopsis(segments, expected)
|
|
self.assertEqual(result, 28.0)
|
|
|
|
def test_no_expected_text_returns_none(self):
|
|
self.assertIsNone(markers.find_intro_end_via_synopsis([("anything", 0.0, 1.0)], None))
|
|
self.assertIsNone(markers.find_intro_end_via_synopsis([("anything", 0.0, 1.0)], ""))
|
|
|
|
def test_no_segments_returns_none(self):
|
|
self.assertIsNone(markers.find_intro_end_via_synopsis([], "some expected text"))
|
|
|
|
def test_unrelated_content_does_not_align(self):
|
|
# A host's own content that happens to share a few common words
|
|
# with the expected synopsis must not be mistaken for it -- the
|
|
# min_total_matched_words / min_block_words floor should reject
|
|
# weak, scattered single-word overlaps.
|
|
expected = (
|
|
"This is Hacker Public Radio episode 4000 for Friday the 1st of January 2021. "
|
|
"Todays show is entitled. Introduction to Rust. It is hosted by Dave, and is "
|
|
"about 20 minutes long. It carries a clean flag. The summary is. "
|
|
"A gentle introduction to the Rust programming language."
|
|
)
|
|
segments = [
|
|
("So today I want to talk about my garden and the tomatoes I'm growing this year.", 0.0, 6.0),
|
|
("It's been a long season and I think the summary is that it's going well.", 6.0, 12.0),
|
|
]
|
|
result = markers.find_intro_end_via_synopsis(segments, expected)
|
|
self.assertIsNone(result)
|
|
|
|
def test_coincidental_mid_transcript_resemblance_is_not_trusted(self):
|
|
# The expected text happens to resemble something later in the
|
|
# transcript, but NOT near the start -- there's no confirmed
|
|
# anchor that the episode actually opens with the TTS block, so
|
|
# this must not be trusted (leading_anchor_words).
|
|
expected = "Todays show is entitled. A Test Topic. The summary is. A short test."
|
|
segments = [
|
|
("Completely unrelated host chatter that goes on for a while before anything else.", 0.0, 10.0),
|
|
("More unrelated chatter continuing on and on with different topics entirely here.", 10.0, 20.0),
|
|
("Todays show is entitled. A Test Topic. The summary is. A short test.", 20.0, 24.0),
|
|
]
|
|
result = markers.find_intro_end_via_synopsis(segments, expected)
|
|
self.assertIsNone(result)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|