Add songforge as independent repo with path layout.
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
+224
@@ -0,0 +1,224 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""歌词容量与时长对应关系。
|
||||
|
||||
这是"死心塌地"的部分:不看模型表现,只按音乐结构算出这段时间到底能唱多少字,
|
||||
填字必须落进区间,否则 check 直接报错,不给侥幸。
|
||||
|
||||
推导:
|
||||
每小节秒数 = 60 / BPM * 每小节拍数
|
||||
总小节 = 时长 / 每小节秒数
|
||||
可唱小节 = (总小节 - 前奏小节) * 可唱比例
|
||||
音节容量 = 可唱小节 * 每小节音节区间
|
||||
填充率 = 实际音节 / 容量上限(仅诊断用,不作为放行闸门)
|
||||
|
||||
阈值来源(重要):
|
||||
syllable_per_bar_* 与 ideal_line_syllable 不是理论推导,而是用 remake_v5.py 里
|
||||
8 首用户已实际生成并认可的歌反推出来的真实工作区间:
|
||||
每可唱小节音节 4.56 ~ 7.64 (均值 6.17)
|
||||
每句音节 5.9 ~ 7.4 (均值 6.7)
|
||||
改这两个数之前请先跑 selftest 的"实歌回归",否则会误杀已验证可生成的歌词。
|
||||
历史坑:曾按理论值设成"每拍 2.6~4.4 音节、每句下限 7",结果 8 首实歌
|
||||
全部被判歌词过少(实测每拍只有 1.14~1.91 音节)。理论值不能当阈值用。
|
||||
"""
|
||||
import math
|
||||
import re
|
||||
|
||||
from ..core.errors import LyricDensityError
|
||||
|
||||
SEC_RE = re.compile(r"^\[(intro|instrumental|verse|pre-?chorus|chorus|hook|"
|
||||
r"rap|bridge|break|breakdown|build|drop|final drop|"
|
||||
r"post-?drop|outro|final hook|final chorus)\]",
|
||||
re.I)
|
||||
|
||||
|
||||
def lyric_len(text):
|
||||
cn = sum(1 for c in text if "\u4e00" <= c <= "\u9fff")
|
||||
en = len(re.findall(r"[A-Za-z][A-Za-z'\-]*", text))
|
||||
return cn, en
|
||||
|
||||
|
||||
|
||||
|
||||
def kana_count(text):
|
||||
"""假名音节数:平假名 + 片假名 + 半角浊音。
|
||||
|
||||
为什么必须单独计数(中日混合歌词实测踩到的坑):
|
||||
lyric_len 只认汉字和英文字母,日文假名一个都不数。
|
||||
"お誕生日おめでとう 一棠ちゃん" 这行真实可唱约 13 音节,
|
||||
原实现只算得到 5 个汉字 + 1 个英文字(2),少算一大截,
|
||||
于是 check 把一份写满的正常歌词误判成"歌词过少",
|
||||
写词的人只能靠加无意义的字去凑数,越凑越空洞。
|
||||
|
||||
排除两类字符,它们不独立占音节:
|
||||
1. 小书写假名 ぁぃぅぇぉゃゅょゎ ァィゥェォャュョヮ ヵヶ
|
||||
以及促音 っ —— 它们依附在前一个音节上。
|
||||
2. 长音符号 ー ゝゞヽヾ —— 它们延长前一个音,不新增音节。
|
||||
"""
|
||||
small = (u"\u3041\u3043\u3045\u3047\u3049\u3063"
|
||||
u"\u3083\u3085\u3087\u308e"
|
||||
u"\u30a1\u30a3\u30a5\u30a7\u30a9\u30c3"
|
||||
u"\u30e3\u30e5\u30e7\u30ee\u30f5\u30f6"
|
||||
u"\u30fc\u309d\u309e\u30fd\u30fe")
|
||||
body = "".join(c for c in text if c not in small)
|
||||
return len(re.findall(r"[\u3041-\u309F\u30A0-\u30FF\uFF66-\uFF9F]", body))
|
||||
|
||||
|
||||
def syllable(text):
|
||||
"""可唱近似音节数:汉字*1 + 英文词*2 + 假名*1。"""
|
||||
cn, en = lyric_len(text)
|
||||
return cn + en * 2 + kana_count(text)
|
||||
|
||||
|
||||
def only_lyrics(text):
|
||||
"""剥掉结构标记与 [Instrumental: ...] 描述,只留真正被唱的正文。"""
|
||||
out = []
|
||||
for ln in text.split("\n"):
|
||||
s = ln.strip()
|
||||
if not s or s.startswith("["):
|
||||
continue
|
||||
out.append(s)
|
||||
return "\n".join(out)
|
||||
|
||||
|
||||
def sections(text):
|
||||
"""按结构标记切段,返回 [(tag, body_text)]。"""
|
||||
out = []
|
||||
tag = "unknown"
|
||||
buf = []
|
||||
for ln in text.split("\n"):
|
||||
s = ln.strip()
|
||||
if s.startswith("["):
|
||||
m = SEC_RE.match(s)
|
||||
if m:
|
||||
if buf:
|
||||
out.append((tag, "\n".join(buf).strip()))
|
||||
tag = m.group(1).lower()
|
||||
buf = []
|
||||
continue
|
||||
buf.append(ln)
|
||||
if buf:
|
||||
out.append((tag, "\n".join(buf).strip()))
|
||||
return out
|
||||
|
||||
|
||||
def bars(duration, bpm, beats_per_bar=4):
|
||||
return duration / (60.0 / bpm * beats_per_bar)
|
||||
|
||||
|
||||
def pick(cfg_lyrics, profile=None):
|
||||
"""按档取出密度阈值。
|
||||
|
||||
default 档直接用 lyrics 顶层字段(保持向后兼容);
|
||||
其它档从 lyrics.profiles.<name> 覆盖顶层同名字段后返回。
|
||||
这样加档不用改任何计算公式,只加配置。
|
||||
"""
|
||||
if not profile or profile == "default":
|
||||
return cfg_lyrics
|
||||
prof = (cfg_lyrics.get("profiles") or {}).get(profile)
|
||||
if not prof:
|
||||
raise LyricDensityError(
|
||||
"未知密度档 '%s',可选:default / %s"
|
||||
% (profile, ", ".join(sorted((cfg_lyrics.get("profiles") or {})))))
|
||||
out = dict(cfg_lyrics)
|
||||
out.update({k: v for k, v in prof.items() if not k.startswith("_")})
|
||||
out["_profile"] = profile
|
||||
return out
|
||||
|
||||
|
||||
def capacity(duration, bpm, cfg_lyrics):
|
||||
"""返回该时长/BPM 下的音节区间与结构量。
|
||||
|
||||
区间由"每可唱小节音节数"决定,这是唯一闸门;填充率只做诊断。
|
||||
"""
|
||||
beats = 4 # time_signature 固定 4 拍
|
||||
total = bars(duration, bpm, beats)
|
||||
sing = max(1.0, (total - cfg_lyrics["intro_bars"])
|
||||
* cfg_lyrics["sing_bar_ratio"])
|
||||
lo = sing * cfg_lyrics["syllable_per_bar_min"]
|
||||
hi = sing * cfg_lyrics["syllable_per_bar_max"]
|
||||
return dict(total_bars=total, sing_bars=sing, lo=lo, hi=hi,
|
||||
beats_per_bar=beats)
|
||||
|
||||
|
||||
def window(duration, bpm, cfg_lyrics):
|
||||
"""check 实际放行的音节窗口(整数化)。
|
||||
|
||||
对外所有"该写多少字"的表述都必须来自这里,避免文档与代码不一致。
|
||||
"""
|
||||
cap = capacity(duration, bpm, cfg_lyrics)
|
||||
lo, hi = cap["lo"], cap["hi"]
|
||||
if hi < lo:
|
||||
lo = hi = cap["lo"]
|
||||
return int(math.ceil(lo)), int(math.floor(hi))
|
||||
|
||||
|
||||
def analyse(lyrics, duration, bpm, cfg_lyrics):
|
||||
body = only_lyrics(lyrics)
|
||||
syl = syllable(body)
|
||||
lines = [l for l in body.split("\n") if l.strip()]
|
||||
cap = capacity(duration, bpm, cfg_lyrics)
|
||||
wlo, whi = window(duration, bpm, cfg_lyrics)
|
||||
fill = syl / cap["hi"] if cap["hi"] else 0.0
|
||||
per_line = syl / len(lines) if lines else 0.0
|
||||
return dict(syllables=syl, lines=len(lines), per_line=round(per_line, 1),
|
||||
fill=round(fill, 3), total_bars=round(cap["total_bars"], 1),
|
||||
sing_bars=round(cap["sing_bars"], 1),
|
||||
lo=int(cap["lo"]), hi=int(cap["hi"]),
|
||||
win_lo=wlo, win_hi=whi)
|
||||
|
||||
|
||||
def target_words(duration, bpm, cfg_lyrics):
|
||||
"""给写词的人用的目标字数区间(死心塌地填字依据)。
|
||||
|
||||
返回 (建议字数, 下限, 上限)。下限上限与 check 实际放行窗口完全一致。
|
||||
建议字数取实测均值 6.17 音节/小节对应的位置,不取理论中点,
|
||||
因为理论中点会把歌写得比已验证作品明显更稀或明显更密。
|
||||
"""
|
||||
cap = capacity(duration, bpm, cfg_lyrics)
|
||||
wlo, whi = window(duration, bpm, cfg_lyrics)
|
||||
mid = cap["sing_bars"] * 6.17 # 实测工作区均值
|
||||
mid = max(wlo, min(mid, whi))
|
||||
return int(mid), wlo, whi
|
||||
|
||||
|
||||
def check(lyrics, duration, bpm, cfg_lyrics):
|
||||
"""死心塌地校验。返回问题列表,空列表代表通过。"""
|
||||
st = analyse(lyrics, duration, bpm, cfg_lyrics)
|
||||
errs = []
|
||||
if st["syllables"] == 0:
|
||||
errs.append("正文为空,没有任何可唱歌词")
|
||||
return errs, st
|
||||
if st["syllables"] < st["win_lo"]:
|
||||
errs.append(
|
||||
"歌词过少:%d 音节(放行下限 %d,还缺约 %d)。"
|
||||
"%ds / %dBPM 共 %.0f 小节,前奏占 %d 小节,实际可唱 %.0f 小节,"
|
||||
"按实测密度需要 %d~%d 音节。字太少模型会硬拉长音、抢拍、吞字。"
|
||||
% (st["syllables"], st["win_lo"], st["win_lo"] - st["syllables"],
|
||||
duration, bpm, st["total_bars"], cfg_lyrics["intro_bars"],
|
||||
st["sing_bars"], st["win_lo"], st["win_hi"]))
|
||||
elif st["syllables"] > st["win_hi"]:
|
||||
errs.append(
|
||||
"歌词过多:%d 音节(放行上限 %d,超出约 %d)。"
|
||||
"实际可唱 %.0f 小节,按实测密度上限只到 %d 音节。"
|
||||
"字太多会加速、丢字、句尾被吃掉。"
|
||||
% (st["syllables"], st["win_hi"],
|
||||
st["syllables"] - st["win_hi"],
|
||||
st["sing_bars"], st["win_hi"]))
|
||||
if st["per_line"] > cfg_lyrics["line_syllable_max"]:
|
||||
errs.append("平均每句 %.1f 音节,超过上限 %d,换气点不足,容易抢拍"
|
||||
% (st["per_line"], cfg_lyrics["line_syllable_max"]))
|
||||
elif st["per_line"] < cfg_lyrics["ideal_line_syllable"][0]:
|
||||
errs.append("平均每句 %.1f 音节偏少(实测下限约 %.1f),句子太碎,"
|
||||
"容易出现拖腔填充"
|
||||
% (st["per_line"],
|
||||
cfg_lyrics["ideal_line_syllable"][0]))
|
||||
return errs, st
|
||||
|
||||
|
||||
def enforce(lyrics, duration, bpm, cfg_lyrics):
|
||||
errs, st = check(lyrics, duration, bpm, cfg_lyrics)
|
||||
if errs:
|
||||
raise LyricDensityError(
|
||||
"歌词与时长不匹配(死心塌地时长对应关系):\n - "
|
||||
+ "\n - ".join(errs))
|
||||
return st
|
||||
@@ -0,0 +1,34 @@
|
||||
[verse]
|
||||
ooh ooh
|
||||
mmm mmm
|
||||
ooh ooh
|
||||
low and slow
|
||||
|
||||
[chorus]
|
||||
ooh
|
||||
let it go
|
||||
ooh ooh
|
||||
hold me tight
|
||||
|
||||
[post-drop]
|
||||
mmm
|
||||
under the light
|
||||
mmm mmm
|
||||
without a doubt
|
||||
|
||||
[chorus]
|
||||
ooh ooh
|
||||
let it go
|
||||
ooh ooh
|
||||
hold me tight
|
||||
|
||||
[bridge]
|
||||
mmm
|
||||
ooh ooh
|
||||
mmm
|
||||
ooh ooh
|
||||
|
||||
[outro]
|
||||
ooh
|
||||
mmm
|
||||
ooh
|
||||
Reference in New Issue
Block a user