khodowany
377 lines
20 KiB
Python
377 lines
20 KiB
Python
"""Constrained, deterministically seeded autoregressive musical sampling.
|
|
|
|
The pooled model proposes joint note/rest, duration and pitch events. Complete
|
|
expression actions include their real resolution. Guitar and chord/function
|
|
validity precede sampling. No target access, hand-authored melody scorer or
|
|
legacy fallback. A bounded restart handles an exhausted/entirely silent sample.
|
|
"""
|
|
from __future__ import annotations
|
|
import collections
|
|
import dataclasses
|
|
import fractions
|
|
import hashlib
|
|
import math
|
|
import random
|
|
|
|
import generator.harmony
|
|
import generator.model
|
|
import generator.solo.expressions
|
|
import generator.solo.groups
|
|
import generator.solo.learned
|
|
import generator.solo.types
|
|
import generator.vocabulary
|
|
|
|
class SearchExhausted(ValueError):
|
|
pass
|
|
|
|
@dataclasses.dataclass(frozen=True)
|
|
class State:
|
|
events: tuple = ()
|
|
notes: tuple = ()
|
|
contracts: tuple = ()
|
|
history: tuple = ()
|
|
previous: int | None = None
|
|
cost: float = 0.
|
|
|
|
def event_key(events): return tuple((a, b, -1 if p is None else p) for a, b, p in events)
|
|
|
|
class Decoder:
|
|
def __init__(self, analysis, harmony, model, role, start, end, *, expressions_enabled=True, attempts=4, seed='', composition=None):
|
|
self.composition = composition or generator.vocabulary.current()
|
|
if type(attempts) is not int or not 1 <= attempts <= 16:
|
|
raise ValueError('attempts must be between 1 and 16')
|
|
self.analysis, self.harmony, self.model, self.role = analysis, harmony, model, role
|
|
self.start, self.end = start, end
|
|
self.attempts = attempts
|
|
source = tuple((str(n.start), str(n.end), n.pitch.number()) for n in analysis.melody)
|
|
self.seed = seed or hashlib.sha256(repr((source, role, generator.solo.learned.VERSION)).encode()).hexdigest()
|
|
self.expressions_enabled = expressions_enabled
|
|
self.low, self.high = harmony.profile.register
|
|
limits = self.composition.data('roles')['difficulty']
|
|
self.durations = tuple(d for d in model.durations if 0 < d <= 4 and d.denominator in (1, 2, 4) and
|
|
(d.denominator != 4 or analysis.tempo <= limits['sixteenth_max_bpm']))
|
|
self.allow_triplets = analysis.tempo <= limits['triplet_max_bpm']
|
|
self._actions = {}
|
|
self._context = {}
|
|
self._pitches = {}
|
|
self._colors = {}
|
|
self._permissions = {}
|
|
self.trace = []
|
|
self.counts = collections.Counter()
|
|
def context(self, time):
|
|
if time not in self._context:
|
|
harmonic, root, future = generator.solo.learned.chord_context(self.harmony, time)
|
|
self._context[time] = (harmonic, root, generator.solo.learned.phase_at(self.analysis, time), generator.solo.learned.source_feature(self.analysis, time, root), future)
|
|
return self._context[time]
|
|
def pitch(self, number, time):
|
|
span = self.harmony.at(time)
|
|
identity = (number, span.start if span else None)
|
|
if identity not in self._pitches:
|
|
self._pitches[identity] = self._spell(number, time)
|
|
return self._pitches[identity]
|
|
def _spell(self, number, time):
|
|
span = self.harmony.at(time)
|
|
if span and span.chord != 'N.C.':
|
|
chord = generator.solo.expressions.parsed_chord(span.chord)
|
|
for degree, alter in generator.harmony.degrees(chord).items():
|
|
p = generator.solo.expressions.degree_pitch(chord, degree, alter, number)
|
|
if p.number() == number:
|
|
return p
|
|
for letter, alter in zip(generator.model.LETTERS, span.key['alterations']):
|
|
accidental = generator.model.fraction(alter)
|
|
if (generator.model.NATURAL[letter] + accidental) % 12 == number % 12:
|
|
return generator.solo.types.Pitch(letter, accidental, int((number - generator.model.NATURAL[letter] - accidental) // 12) - 1)
|
|
names = (('C', 0), ('D', -1), ('D', 0), ('E', -1), ('E', 0), ('F', 0), ('F', 1), ('G', 0), ('A', -1), ('A', 0), ('B', -1), ('B', 0))
|
|
letter, alter = names[number % 12]
|
|
return generator.solo.types.Pitch(letter.lower(), fractions.Fraction(alter), number // 12 - 1)
|
|
def note(self, a, b, p, role='learned'):
|
|
pitch = p if isinstance(p, generator.solo.types.Pitch) else self.pitch(p, a)
|
|
return generator.solo.types.Note(a, b, pitch, role=role, event_id=f'{a}:{b}:{pitch.number()}')
|
|
def color_bases(self, n):
|
|
key = (n.start, n.end, n.pitch.number())
|
|
if key in self._colors:
|
|
return self._colors[key]
|
|
bases = []
|
|
regions = [(None, n)]
|
|
regions.extend((s.start, dataclasses.replace(n, start=s.start)) for s in self.harmony.spans
|
|
if n.start < s.start < n.end and s.start - n.start <= fractions.Fraction(self.composition.data('harmony')['anticipation_max']))
|
|
for boundary, arrived in regions:
|
|
exposed = [s for s, _, _ in self.harmony.segments(arrived) if n.pitch.number() % 12 not in s.roles.basic | s.roles.specified]
|
|
if not exposed:
|
|
continue
|
|
for rule in self.composition.data('harmony')['colors']:
|
|
if arrived.end - arrived.start > fractions.Fraction(rule['max_beats']):
|
|
continue
|
|
if any(s.chord == 'N.C.' or not generator.solo.expressions.eligible_color(rule, s, self.harmony) or
|
|
generator.solo.expressions.degree_pitch(generator.solo.expressions.parsed_chord(s.chord), rule['degree'], rule['alter'], n.pitch.number()).number() != n.pitch.number()
|
|
for s in exposed):
|
|
continue
|
|
bases.append((rule, boundary))
|
|
self._colors[key] = tuple(bases)
|
|
return self._colors[key]
|
|
def color_contract(self, n, target, rule, boundary):
|
|
span = self.harmony.at(boundary if boundary is not None else n.start)
|
|
if not span:
|
|
return None
|
|
kind = 'anticipated_color' if boundary is not None else 'color'
|
|
return generator.solo.types.ExpressionContract(n.event_id + ':' + rule['id'] + ':' + str(boundary), kind, rule['id'], (n,), target, span.chord, boundary)
|
|
def permission(self, n):
|
|
key = (n.start, n.end, n.pitch.number())
|
|
if key not in self._permissions:
|
|
self._permissions[key] = self._permission(n)
|
|
return self._permissions[key]
|
|
def _permission(self, n):
|
|
"""Find justified color/anticipation support, never authorize by label."""
|
|
# Source spans are contiguous. These are precisely the ordinary-event
|
|
# branches of Harmony.evaluate, without rebuilding an empty contract map.
|
|
if self.harmony.at(n.start) and n.end <= self.harmony.spans[-1].end:
|
|
if n.pitch.number() % 12 in self.harmony.members(n.start, n.end):
|
|
return ()
|
|
if n.end - n.start < 2 and n.pitch.number() % 12 in self.harmony.permitted(n.start, n.end):
|
|
return ()
|
|
if not self.expressions_enabled:
|
|
return None
|
|
span = self.harmony.at(n.start)
|
|
if not span or span.chord == 'N.C.':
|
|
return None
|
|
for rule, boundary in self.color_bases(n):
|
|
if rule.get('resolve'):
|
|
continue
|
|
c = self.color_contract(n, n, rule, boundary)
|
|
if self.harmony.evaluate((n,), complete=True, expressions=(c,), infer=False).valid:
|
|
return tuple([c])
|
|
for arriving in self.harmony.spans:
|
|
if n.start < arriving.start < n.end and arriving.start - n.start <= fractions.Fraction(self.composition.data('harmony')['anticipation_max']):
|
|
c = generator.solo.types.ExpressionContract(n.event_id + ':anticipation', 'anticipation', 'early_chord_tone', (n,), n, arriving.chord, arriving.start)
|
|
if self.harmony.evaluate((n,), complete=True, expressions=(c,), infer=False).valid:
|
|
return tuple([c])
|
|
return None
|
|
def tails(self, n, target):
|
|
"""Finite resolution timing: direct, real space, or one valid intervening note."""
|
|
gap = target.start - n.end
|
|
if gap < 0:
|
|
return
|
|
if gap == 0:
|
|
yield ((n.start, n.end, n.pitch.number()), (target.start, target.end, target.pitch.number())), (n, target)
|
|
return
|
|
yield ((n.start, n.end, n.pitch.number()), (n.end, target.start, None), (target.start, target.end, target.pitch.number())), (n, target)
|
|
windows = {(n.end, target.start)} if gap <= 1 else set()
|
|
if gap >= 1:
|
|
windows |= {(n.end, n.end + fractions.Fraction(1, 2)), (target.start - fractions.Fraction(1, 2), target.start)}
|
|
for a, b in sorted(windows):
|
|
for number in range(max(self.low, n.pitch.number() - 3), min(self.high, n.pitch.number() + 3) + 1):
|
|
mid = self.note(a, b, number)
|
|
if number in (n.pitch.number(), target.pitch.number()) or not self.harmony.ordinary(mid):
|
|
continue
|
|
events = [(n.start, n.end, n.pitch.number())]
|
|
if a > n.end:
|
|
events.append((n.end, a, None))
|
|
events.append((a, b, number))
|
|
if b < target.start:
|
|
events.append((b, target.start, None))
|
|
events.append((target.start, target.end, target.pitch.number()))
|
|
yield tuple(events), (n, mid, target)
|
|
def resolutions(self, n):
|
|
"""Joint color/delayed-approach actions; the destination is never optional."""
|
|
requests = []
|
|
for rule, boundary in self.color_bases(n):
|
|
if rule.get('resolve'):
|
|
for gap in (fractions.Fraction(), fractions.Fraction(1, 2), fractions.Fraction(1)):
|
|
if gap <= fractions.Fraction(self.composition.data('harmony')['resolution_gap']):
|
|
requests.append(('color', rule, boundary, n.end + gap, (-2, -1, 1, 2)))
|
|
delay = self.composition.data('lead_ins')['delayed_approach']
|
|
if n.end - n.start <= fractions.Fraction(delay['max_note']) and n.pitch.number() % 12 not in self.harmony.permitted(n.start, n.end):
|
|
for arrival in map(fractions.Fraction, delay['arrivals']):
|
|
if n.end <= n.start + arrival <= n.start + fractions.Fraction(delay['deadline']):
|
|
requests.append(('delayed', delay, None, n.start + arrival, delay['steps']))
|
|
for kind, rule, boundary, arrival, steps in requests:
|
|
for delta in steps:
|
|
number = n.pitch.number() + delta
|
|
if not self.low <= number <= self.high:
|
|
continue
|
|
for hold in (fractions.Fraction(1, 2), fractions.Fraction(1), fractions.Fraction(2)):
|
|
if arrival + hold > self.end or number % 12 not in self.harmony.members(arrival, arrival + hold):
|
|
continue
|
|
target = self.note(arrival, arrival + hold, number, 'destination')
|
|
c = self.color_contract(n, target, rule, boundary) if kind == 'color' else generator.solo.types.ExpressionContract(n.event_id + ':delayed', 'delayed_approach', rule['id'], (n,), target, self.harmony.at(arrival).chord)
|
|
# Color and delayed-approach contracts permit this intervening
|
|
# window. Validate the invariant endpoints once; tails() checks
|
|
# every inserted note's ordinary full-duration permission itself.
|
|
if not self.harmony.evaluate((n, target), complete=True, expressions=(c,), infer=False).valid:
|
|
continue
|
|
for events, ns in self.tails(n, target):
|
|
if not generator.solo.groups.valid(tuple((a, b) for a, b, _ in events)):
|
|
continue
|
|
yield events, ns, (c,)
|
|
def actions(self, time):
|
|
if time in self._actions:
|
|
return self._actions[time]
|
|
result = []
|
|
def add(events, notes, contracts=()): result.append((events, notes, contracts))
|
|
for duration in self.durations:
|
|
end = time + duration
|
|
if end > self.end:
|
|
continue
|
|
add(((time, end, None),), ())
|
|
for number in range(self.low, self.high + 1):
|
|
n = self.note(time, end, number)
|
|
support = self.permission(n)
|
|
if support is not None:
|
|
add(((time, end, number),), (n,), support)
|
|
if self.expressions_enabled and not self.harmony.ordinary(n):
|
|
for events, ns, contracts in self.resolutions(n):
|
|
add(events, ns, contracts)
|
|
rule = self.composition.data('lead_ins')['passing']
|
|
if duration <= fractions.Fraction(rule['max_note']):
|
|
for step in rule['steps']:
|
|
p = number + step
|
|
if not self.low <= p <= self.high:
|
|
continue
|
|
for hold in (fractions.Fraction(1, 2), fractions.Fraction(1), fractions.Fraction(2)):
|
|
if end + hold > self.end:
|
|
continue
|
|
target = self.note(end, end + hold, p)
|
|
extra = self.permission(target)
|
|
if extra is None or any(c.kind not in ('color', 'anticipated_color') for c in extra):
|
|
continue
|
|
c = generator.solo.types.ExpressionContract(n.event_id + ':passing', 'passing', rule['id'], (n,), target, self.harmony.at(end).chord)
|
|
add(((time, end, number), (end, end + hold, p)), (n, target), (c, *extra))
|
|
if self.expressions_enabled:
|
|
limits = self.composition.data('roles')['difficulty']
|
|
for rule in self.composition.data('lead_ins')['patterns']:
|
|
difficulty = rule.get('difficulty')
|
|
if difficulty and self.analysis.tempo > limits[difficulty + '_max_bpm']:
|
|
continue
|
|
# Connections require a concrete preceding note, checked at expansion.
|
|
durations = tuple(map(fractions.Fraction, rule['durations']))
|
|
gaps = tuple(map(fractions.Fraction, rule.get('internal_gaps', ['0'] * (len(durations) - 1))))
|
|
target_time = time + sum(durations, fractions.Fraction()) + sum(gaps, fractions.Fraction()) + fractions.Fraction(rule['gap'])
|
|
span = self.harmony.at(target_time)
|
|
if not span or span.chord == 'N.C.':
|
|
continue
|
|
holds = (fractions.Fraction(1, 3),) if difficulty == 'triplet' else (fractions.Fraction(1, 2), fractions.Fraction(1), fractions.Fraction(2))
|
|
for duration in holds:
|
|
end = target_time + duration
|
|
if end > self.end:
|
|
continue
|
|
for number in range(self.low, self.high + 1):
|
|
if number % 12 not in self.harmony.members(target_time, end):
|
|
continue
|
|
target = self.note(target_time, end, number, 'destination')
|
|
cursor = time
|
|
notes = []
|
|
events = []
|
|
for i, (delta, d) in enumerate(zip(rule['semitones'], durations)):
|
|
n = self.note(cursor, cursor + d, generator.solo.expressions.chromatic(target.pitch, delta), rule['kind'])
|
|
notes.append(n)
|
|
events.append((n.start, n.end, n.pitch.number()))
|
|
cursor = n.end
|
|
gap = gaps[i] if i < len(gaps) else fractions.Fraction(rule['gap'])
|
|
if gap:
|
|
events.append((cursor, cursor + gap, None))
|
|
cursor += gap
|
|
if any(not self.low <= n.pitch.number() <= self.high for n in notes):
|
|
continue
|
|
if not generator.solo.groups.valid(tuple((a, b) for a, b, p in (*events, (target_time, end, number)))):
|
|
continue
|
|
contract = generator.solo.types.ExpressionContract(f'{time}:{number}:{rule["id"]}', rule['kind'], rule['id'], tuple(notes), target, span.chord)
|
|
ns = (*notes, target)
|
|
if rule['kind'] == 'connection':
|
|
# Validation waits for the actual incoming event.
|
|
add((*events, (target_time, end, number)), ns, (contract,))
|
|
elif self.harmony.evaluate(ns, complete=True, expressions=(contract,), infer=False).valid:
|
|
add((*events, (target_time, end, number)), ns, (contract,))
|
|
# Complete ordinary triplet groups; do not leave a third-beat residual.
|
|
if self.allow_triplets and time + 1 <= self.end:
|
|
for number in range(self.low, self.high + 1):
|
|
for direction in (-1, 0, 1):
|
|
numbers = [number]
|
|
cursor = time
|
|
for _ in range(2):
|
|
nxt = next((p for p in range(numbers[-1] + direction, numbers[-1] + direction * 4, direction or 1)
|
|
if self.low <= p <= self.high and p % 12 in self.harmony.permitted(cursor + fractions.Fraction(1, 3), cursor + fractions.Fraction(2, 3))), None) if direction else number
|
|
if nxt is None:
|
|
break
|
|
numbers.append(nxt)
|
|
cursor += fractions.Fraction(1, 3)
|
|
if len(numbers) != 3:
|
|
continue
|
|
ns = tuple(self.note(time + i * fractions.Fraction(1, 3), time + (i + 1) * fractions.Fraction(1, 3), p) for i, p in enumerate(numbers))
|
|
if self.harmony.evaluate(ns, complete=True, infer=False).valid:
|
|
add(tuple((n.start, n.end, n.pitch.number()) for n in ns), ns)
|
|
self._actions[time] = tuple(result)
|
|
self.counts['valid_structures'] += len(result)
|
|
return self._actions[time]
|
|
def extend(self, state, action):
|
|
events, notes, contracts = action
|
|
# Training tokenization merges contiguous silence. Never manufacture a
|
|
# rest-to-rest transition absent from that event representation.
|
|
if state.events and state.events[-1][2] is None and events[0][2] is None:
|
|
return None
|
|
if notes and state.previous is not None and abs(notes[0].pitch.number() - state.previous) > 12:
|
|
return None
|
|
if any(c.kind in ('connection', 'passing') and c.preparation is None for c in contracts):
|
|
if not state.notes:
|
|
return None
|
|
contracts = tuple(dataclasses.replace(c, preparation=state.notes[-1]) if c.kind in ('connection', 'passing') and c.preparation is None else c for c in contracts)
|
|
if self.harmony.ordinary(state.notes[-1]):
|
|
_, error = generator.solo.expressions.validate((state.notes[-1], *notes), contracts, self.harmony, composition=self.composition)
|
|
else:
|
|
_, error = generator.solo.expressions.validate((*state.notes, *notes), (*state.contracts, *contracts), self.harmony, composition=self.composition)
|
|
if error:
|
|
return None
|
|
history = state.history
|
|
previous = state.previous
|
|
cost = state.cost
|
|
for a, b, p in events:
|
|
harmonic, root, phase, source, _ = self.context(a)
|
|
action = generator.solo.learned.token(b - a, p, previous, root)
|
|
context = generator.solo.learned.contexts(harmonic, phase, source, history)
|
|
cost += self.model.cost(action, context)
|
|
if p is not None:
|
|
if previous is None:
|
|
cost += self.model.register_cost(p)
|
|
previous = p
|
|
history = (*history, action)[-4:]
|
|
return State((*state.events, *events), (*state.notes, *notes), (*state.contracts, *contracts), history, previous, cost)
|
|
def compose(self):
|
|
for attempt in range(self.attempts):
|
|
rng = random.Random(self.seed + ':' + str(attempt))
|
|
state = State()
|
|
time = self.start
|
|
trace = []
|
|
while time < self.end:
|
|
actions = self.actions(time)
|
|
options = [s for a in actions if (s := self.extend(state, a)) is not None]
|
|
# Different operator names cannot multiply the probability of identical
|
|
# sounded music. Prefer plain permission when no exception is needed.
|
|
unique = {}
|
|
for s in options:
|
|
signature = event_key(s.events[len(state.events):])
|
|
if signature not in unique or len(s.contracts) < len(unique[signature].contracts):
|
|
unique[signature] = s
|
|
options = sorted(unique.values(), key=lambda s: event_key(s.events[len(state.events):]))
|
|
self.counts['scored_continuations'] += len(options)
|
|
if not options:
|
|
break
|
|
low = min(s.cost - state.cost for s in options)
|
|
weights = [math.exp(-(s.cost - state.cost - low)) for s in options]
|
|
draw = rng.random() * sum(weights)
|
|
selected = options[-1]
|
|
for s, w in zip(options, weights):
|
|
draw -= w
|
|
if draw <= 0:
|
|
selected = s
|
|
break
|
|
trace.append({'time': str(time), 'valid_joint_actions': len(options),
|
|
'selected_events': [(str(a), str(b), p) for a, b, p in selected.events[len(state.events):]],
|
|
'negative_log_likelihood': selected.cost - state.cost})
|
|
state = selected
|
|
time = state.events[-1][1]
|
|
if time == self.end and state.notes:
|
|
self.trace = trace
|
|
self.completed = (state,)
|
|
self.counts['attempts'] = attempt + 1
|
|
return state
|
|
raise SearchExhausted(f'{self.role}: no complete non-silent sample within {self.attempts} deterministic attempts; end={self.end}')
|