Add lyrics pipeline, playlist views, admin toggles, and player polish
Lyrics pipeline (Whisper + Demucs + description alignment):
- New GenerateLyricsJob runs WhisperX with VAD filtering and forced word
alignment, writes per-track JSON to NAS.
- New DecorateLyricsJob calls the active LLM provider to bake one to
several emojis into each line (heavy decoration prompt).
- LyricsDescriptionParser strips heading content, section markers, and
emoji-decoration from a song's description while preserving every
language verbatim.
- correct_whisper_with_description aligner: strong-match anchors only,
vocal-region-aware gap-fill so missing verses land on actual singing.
- Owner UI for generate/regenerate/edit/delete in the player gear.
Admin pages:
- /admin/lyrics toggles for VAD, vocal gap-fill, Demucs, master
- /admin/gpu extracted GPU section, encoder picker, FFmpeg path
- /admin/backup extracted users-and-settings export/import
- /admin/settings now AI/LLM only with provider list and Test button
- /admin/nas-storage hosts NAS settings, repair, disable flow, browser
- Shared partials/settings-styles for a uniform look across pages.
Playlist view tracking:
- Migration adds playlists.view_count and playlist_views dedup table.
- Playlist::bumpViewIfNew increments per device with a one-hour window.
- Tracked from /playlists/{id}, /playlists/share/{token}, /ps/{token},
and /videos/{id}?playlist={token}. Dispatched after-response so it
never blocks the page render.
- Loading a playlist on the video page now runs one query instead of
the four the old getNextVideo/getPreviousVideo path triggered.
- View counts shown on every playlist card and the playlist hero.
Player polish:
- Floating mini-player is draggable, persists its position in
localStorage, clamps to viewport on resize.
- Mini disabled entirely on mobile (less than 768px).
- New gear-menu Mini Player toggle (persists in localStorage) lets the
user disable both scroll-activation and SPA-nav-activation.
- Close button keeps media playing when used on the player's own page.
- SPA navigator now swaps a #page-scripts container so per-page JS
(channel tabs, etc.) gets re-executed after content swaps.
Storage layout:
- Runtime data moved from /storage/* to /data/* and gitignored.
- /ml/venv, /ml/cache, /ml/__pycache__ excluded.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
This commit is contained in:
ghassanandClaude Opus 4.7 committed
1 parent
73527f3781
commit
f98e5415a3
60 files changed
+7920
-2675
No files matched your search
@@ -0,0 +1,109 @@
|
||||
<?php
|
||||
|
||||
namespace App\Support;
|
||||
|
||||
/**
|
||||
* Build an ASS (Advanced SubStation Alpha) subtitle file with word-level
|
||||
* karaoke timing from a lyrics JSON payload (the shape produced by
|
||||
* ml/transcribe.py). Burned into the downloadable mp4 via libass.
|
||||
*
|
||||
* Karaoke fill uses ASS \k tags: each word's \k duration (centiseconds) is the
|
||||
* time it waits before the highlight reaches it, so the cumulative \k before a
|
||||
* word equals its onset relative to the line start. PrimaryColour is the sung
|
||||
* (filled) colour, SecondaryColour the not-yet-sung colour.
|
||||
*/
|
||||
class LyricsAss
|
||||
{
|
||||
/** Render at the same canvas the slideshow uses. */
|
||||
private const W = 1280;
|
||||
private const H = 720;
|
||||
|
||||
/**
|
||||
* Write an .ass file for the given lyrics data. Returns true on success,
|
||||
* false when there are no usable timed lines (caller should skip burning).
|
||||
*/
|
||||
public static function write(array $lyrics, string $outPath): bool
|
||||
{
|
||||
$lines = $lyrics['lines'] ?? [];
|
||||
if (! is_array($lines) || ! $lines) return false;
|
||||
|
||||
$events = [];
|
||||
foreach ($lines as $ln) {
|
||||
$start = $ln['start'] ?? null;
|
||||
$end = $ln['end'] ?? null;
|
||||
if ($start === null || $end === null) continue;
|
||||
|
||||
$words = (isset($ln['words']) && is_array($ln['words']) && $ln['words']) ? $ln['words'] : null;
|
||||
$text = $words
|
||||
? self::karaokeText($words, (float) $start)
|
||||
: self::escape((string) ($ln['text'] ?? ''));
|
||||
if ($text === '') continue;
|
||||
|
||||
// Hold the line a touch past its last word for readability.
|
||||
// Fields per the Format line: Layer,Start,End,Style,Name,MarginL,MarginR,Effect,Text
|
||||
$events[] = 'Dialogue: 0,' . self::ts((float) $start) . ',' . self::ts((float) $end + 0.4)
|
||||
. ',Lyrics,,0,0,,' . $text;
|
||||
}
|
||||
if (! $events) return false;
|
||||
|
||||
$ass = self::header() . implode("\n", $events) . "\n";
|
||||
return file_put_contents($outPath, $ass) !== false;
|
||||
}
|
||||
|
||||
private static function karaokeText(array $words, float $lineStart): string
|
||||
{
|
||||
$out = '';
|
||||
$lead = (int) round((((float) $words[0]['start']) - $lineStart) * 100);
|
||||
if ($lead > 0) $out .= '{\k' . $lead . '}';
|
||||
|
||||
$n = count($words);
|
||||
foreach ($words as $i => $w) {
|
||||
$wStart = (float) $w['start'];
|
||||
$wEnd = (float) $w['end'];
|
||||
$dur = max(1, (int) round(($wEnd - $wStart) * 100));
|
||||
$out .= '{\k' . $dur . '}' . self::escape((string) $w['text']);
|
||||
|
||||
if ($i < $n - 1) {
|
||||
$gap = (int) round((((float) $words[$i + 1]['start']) - $wEnd) * 100);
|
||||
$out .= ($gap > 0 ? '{\k' . $gap . '}' : '') . ' ';
|
||||
}
|
||||
}
|
||||
return $out;
|
||||
}
|
||||
|
||||
/** ASS timestamp: H:MM:SS.cc (centiseconds). */
|
||||
private static function ts(float $t): string
|
||||
{
|
||||
if ($t < 0) $t = 0;
|
||||
$cs = (int) round($t * 100);
|
||||
$h = intdiv($cs, 360000);
|
||||
$m = intdiv($cs % 360000, 6000);
|
||||
$s = intdiv($cs % 6000, 100);
|
||||
$c = $cs % 100;
|
||||
return sprintf('%d:%02d:%02d.%02d', $h, $m, $s, $c);
|
||||
}
|
||||
|
||||
private static function escape(string $s): string
|
||||
{
|
||||
// Strip ASS override delimiters and collapse newlines.
|
||||
$s = str_replace(['{', '}', '\\'], ['(', ')', '/'], $s);
|
||||
return str_replace(["\r\n", "\n", "\r"], ' ', $s);
|
||||
}
|
||||
|
||||
private static function header(): string
|
||||
{
|
||||
// Colours are &HAABBGGRR. Primary = sung (white), Secondary = unsung
|
||||
// (translucent grey), heavy outline + shadow for legibility over artwork.
|
||||
return "[Script Info]\n"
|
||||
. "ScriptType: v4.00+\n"
|
||||
. 'PlayResX: ' . self::W . "\n"
|
||||
. 'PlayResY: ' . self::H . "\n"
|
||||
. "WrapStyle: 0\n"
|
||||
. "ScaledBorderAndShadow: yes\n\n"
|
||||
. "[V4+ Styles]\n"
|
||||
. "Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding\n"
|
||||
. "Style: Lyrics,Sans,54,&H00FFFFFF,&H64C8C8C8,&H00101010,&H80000000,-1,0,0,0,100,100,0,0,1,3,2,2,80,80,70,1\n\n"
|
||||
. "[Events]\n"
|
||||
. "Format: Layer, Start, End, Style, Name, MarginL, MarginR, Effect, Text\n";
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,144 @@
|
||||
<?php
|
||||
|
||||
namespace App\Support;
|
||||
|
||||
/**
|
||||
* Extract clean lyric lines from a video's free-text description.
|
||||
*
|
||||
* Many users paste the song's lyrics into the description with section markers,
|
||||
* emoji decorations, instrument tags, etc. When that's present we want to USE
|
||||
* those exact lines (and let the pipeline only do the *sync*, not the
|
||||
* transcription), because they're far more accurate than anything Whisper can
|
||||
* derive from sung audio.
|
||||
*
|
||||
* Returns an empty array when no usable lyric block is found.
|
||||
*/
|
||||
class LyricsDescriptionParser
|
||||
{
|
||||
/** Heuristic threshold: descriptions with fewer cleaned lines aren't worth aligning. */
|
||||
private const MIN_LYRIC_LINES = 4;
|
||||
|
||||
public static function extract(?string $desc): array
|
||||
{
|
||||
if (! $desc) return [];
|
||||
|
||||
// HTML descriptions use <br> for line breaks — convert those (and other
|
||||
// block-ending tags) into real newlines BEFORE stripping tags, otherwise
|
||||
// the entire body collapses into one long run-on line.
|
||||
// Heading tags (<h1>…<h6>) carry the song title — drop their content
|
||||
// entirely so the title never leaks into the lyric list.
|
||||
$text = preg_replace('/<\s*h[1-6][^>]*>.*?<\s*\/\s*h[1-6]\s*>/isu', "\n", $desc);
|
||||
$text = preg_replace('/<\s*br\s*\/?>/i', "\n", $text);
|
||||
$text = preg_replace('/<\s*\/\s*(p|div|li|tr|blockquote)\s*>/i', "\n", $text);
|
||||
$text = strip_tags($text);
|
||||
// Decode HTML entities ( , &, etc.) so the comparison later isn't fooled.
|
||||
$text = html_entity_decode($text, ENT_QUOTES | ENT_HTML5, 'UTF-8');
|
||||
$text = preg_replace('/\r\n|\r/u', "\n", $text);
|
||||
|
||||
// First pass: clean each line and flag section headers (Verse / Ritornello
|
||||
// / Bridge / etc.) so they can be dropped — those aren't sung.
|
||||
$cleaned = [];
|
||||
foreach (explode("\n", $text) as $line) {
|
||||
$line = self::cleanLine($line);
|
||||
if ($line === null) continue;
|
||||
$cleaned[] = ['text' => $line, 'header' => self::isSectionHeader($line)];
|
||||
}
|
||||
|
||||
// Title detection: if the first non-header line is immediately followed by
|
||||
// a section header (e.g. "Figlio Mio — Viaggio di Vita" then "Verso 1"),
|
||||
// that first line is the song title — drop it too.
|
||||
$firstIdx = null;
|
||||
foreach ($cleaned as $i => $c) {
|
||||
if (! $c['header']) { $firstIdx = $i; break; }
|
||||
}
|
||||
$dropTitle = false;
|
||||
if ($firstIdx !== null) {
|
||||
for ($j = $firstIdx + 1; $j < count($cleaned); $j++) {
|
||||
if ($cleaned[$j]['header']) { $dropTitle = true; break; }
|
||||
break; // first thing after is a real lyric line → not a title block
|
||||
}
|
||||
}
|
||||
|
||||
$out = [];
|
||||
foreach ($cleaned as $i => $c) {
|
||||
if ($c['header']) continue;
|
||||
if ($dropTitle && $i === $firstIdx) continue;
|
||||
$out[] = $c['text'];
|
||||
}
|
||||
|
||||
// Avoid mistakenly aligning non-lyric descriptions (a credit line, a URL,
|
||||
// etc.). Require at least a handful of plausible lyric lines.
|
||||
if (count($out) < self::MIN_LYRIC_LINES) return [];
|
||||
|
||||
return $out;
|
||||
}
|
||||
|
||||
/**
|
||||
* True when a line is a section marker (Verse / Chorus / Bridge / Outro /
|
||||
* their many translations) rather than a sung lyric. Matches the WHOLE line
|
||||
* so a real lyric containing one of these words isn't mistakenly dropped.
|
||||
*/
|
||||
private static function isSectionHeader(string $line): bool
|
||||
{
|
||||
$t = mb_strtolower(trim($line));
|
||||
if ($t === '') return false;
|
||||
|
||||
$roots = [
|
||||
'intro', 'outro', 'interlude', 'instrumental',
|
||||
'verse', 'verso', 'verset', 'couplet', 'estrofa', 'strofa',
|
||||
'chorus', 'ritornello', 'refrain', 'refrão', 'refrao', 'coro', 'estribillo',
|
||||
'pre[\s\-]?chorus', 'pre[\s\-]?ritornello', 'pre[\s\-]?coro',
|
||||
'pre[\s\-]?refrain', 'pre[\s\-]?refrão', 'pré[\s\-]?refrain',
|
||||
'bridge', 'ponte', 'puente', 'pont', 'brücke', 'brucke',
|
||||
'hook', 'drop', 'breakdown', 'tag', 'vamp', 'coda', 'reprise',
|
||||
// CJK / Thai / Arabic / Korean
|
||||
'サビ', 'コーラス', 'バース', 'ブリッジ', 'イントロ', 'アウトロ', 'フック', '間奏',
|
||||
'ท่อน', 'คอรัส', 'ฮุก', 'บริดจ์', 'อินโทร', 'เอาท์โทร',
|
||||
'前奏', '副歌', '桥段', '主歌', '尾奏',
|
||||
'كورس', 'بريدج', 'كوبليه',
|
||||
'후렴', '브릿지', '인트로', '아웃트로', '훅',
|
||||
];
|
||||
$rootRe = implode('|', $roots);
|
||||
// Optional trailing number, "final/finale/reprise", roman numerals.
|
||||
$pattern = '/^(?:' . $rootRe . ')[\s\d:\-—\.]*(?:final|finale|reprise|ii|iii|iv|v|vi|2|3|4|5)?\s*$/iu';
|
||||
return (bool) preg_match($pattern, $t);
|
||||
}
|
||||
|
||||
/** Returns the cleaned line, or null if it should be discarded. */
|
||||
private static function cleanLine(string $line): ?string
|
||||
{
|
||||
$line = trim($line);
|
||||
if ($line === '') return null;
|
||||
|
||||
// Strip markdown emphasis (* _ ~) and leading list bullets / quote markers.
|
||||
$line = preg_replace('/^[\s>\-\*•♪♫·]+/u', '', $line);
|
||||
$line = preg_replace('/[\*_~`]+/u', '', $line);
|
||||
|
||||
// Drop instrument / section annotations inside Japanese-style brackets:
|
||||
// 【 箏・尺八・篠笛・優しい歌声 】 — these aren't lyrics.
|
||||
$line = preg_replace('/【[^】]*】/u', '', $line);
|
||||
$line = preg_replace('/〔[^〕]*〕/u', '', $line);
|
||||
$line = preg_replace('/\[\[[^\]]*\]\]/u', '', $line);
|
||||
|
||||
// Strip emoji / pictographic symbols and the invisible glue that often
|
||||
// sticks to them (variation selectors, ZWJ) so nothing leaves behind a
|
||||
// bare diacritic when the visible emoji is removed.
|
||||
$line = preg_replace(
|
||||
'/[\x{1F000}-\x{1FFFF}\x{2600}-\x{27BF}\x{2B00}-\x{2BFF}\x{0F3A}-\x{0F3D}\x{FE00}-\x{FE0F}\x{200B}-\x{200F}\x{2060}]/u',
|
||||
'', $line
|
||||
);
|
||||
|
||||
// Collapse internal whitespace.
|
||||
$line = preg_replace('/\s+/u', ' ', $line);
|
||||
$line = trim($line);
|
||||
|
||||
if ($line === '') return null;
|
||||
|
||||
// Must contain at least one letter (Unicode), and at least 3 characters
|
||||
// after stripping — discards "🌸 平穏 🌸" (header) and "──" separators.
|
||||
if (! preg_match('/\p{L}/u', $line)) return null;
|
||||
if (mb_strlen($line) < 3) return null;
|
||||
|
||||
return $line;
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user