Files
songforge/config/loader.py
T

211 lines
7.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""配置加载与覆盖。
优先级:命令行 > 环境变量 > local.toml|json > default.toml|json > DEFAULTS。
算法配置用 TOML(与 ComfyUI workflow JSON 分流)。
styles.json / lexicon.json / baseline/*.json 仍是数据文件,保持 JSON。
本机绝对路径只写 local.toml(gitignore)。
"""
import copy
import json
import os
import sys
try:
import tomllib
except ModuleNotFoundError: # Python < 3.11
import tomli as tomllib # type: ignore
# config/loader.py -> 仓根
PKG_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
ROOT = PKG_ROOT
CONFIG_DIR = os.path.join(PKG_ROOT, "config")
DEFAULTS = {
"engine": {"server": "http://127.0.0.1:8188", "timeout_sec": 3600,
"poll_interval_sec": 10, "submit_retries": 3},
"model": {"checkpoint": "ace_step_1.5_turbo_swl_fused.safetensors",
"lora": "swl_voice_best_ep257.safetensors",
"lora_model_strength": 0.5, "lora_clip_strength": 0.5,
"denied_checkpoints": ["yue2_3b_int8_convrot.safetensors",
"ace_step_1.5_turbo_aio.safetensors"]},
"sampler": {"shift": 5.5, "sampling": "flow", "steps": 28, "cfg": 2.0,
"sampler_name": "euler", "scheduler": "simple", "denoise": 1.0},
"encode": {"cfg_scale": 3.0, "temperature": 0.68, "top_p": 0.88,
"top_k": 50, "min_p": 0.02, "generate_audio_codes": True,
"timesignature": "4"},
"paths": {"workflow_template": "workflows/template.json",
"runs_dir": "data/runs",
"tmp_dir": "data/tmp",
"lyrics_dir": "input/lyrics",
"qc_cache_dir": "cache/qc",
"style_cache_dir": "cache/style",
"index_dir": "index",
"catalog_file": "index/catalog.jsonl",
"baseline_dir": "config/baseline",
"comfy_root": None,
"qc_python": None,
"music_dir": None,
"output_prefix": "MyMusic",
"output_format": "flac"},
"song": {"language": "zh", "time_signature": "4",
"duration_range": [150, 200],
"duration_extra_ranges": [[100, 130]]},
"lyrics": {"sing_bar_ratio": 0.70, "intro_bars": 8,
"syllable_per_bar_min": 4.40, "syllable_per_bar_max": 7.80,
"line_syllable_max": 12, "ideal_line_syllable": [5, 12],
"profiles": {
"sparse": {
"sing_bar_ratio": 0.25,
"syllable_per_bar_min": 4.40,
"syllable_per_bar_max": 7.80,
"line_syllable_max": 12,
"ideal_line_syllable": [3, 12],
}
}},
"rules": {"trigger_word": "swlvoice", "intro_bars": 8},
}
def _deep_merge(base, patch):
for k, v in patch.items():
if k.startswith("_"):
continue
if isinstance(v, dict) and isinstance(base.get(k), dict):
_deep_merge(base[k], v)
else:
base[k] = v
return base
def _read_json(name):
p = os.path.join(CONFIG_DIR, name)
if not os.path.isfile(p):
return {}
with open(p, encoding="utf-8") as f:
return json.load(f)
def _read_toml(name):
p = os.path.join(CONFIG_DIR, name)
if not os.path.isfile(p):
return {}
with open(p, "rb") as f:
return tomllib.load(f)
def _read_layer(basename):
"""同名 .json 与 .toml:先 json 再 toml,toml 覆盖(迁移期兼容)。"""
out = {}
_deep_merge(out, _read_json(basename + ".json"))
_deep_merge(out, _read_toml(basename + ".toml"))
return out
def load(overrides=None):
"""返回最终配置 dict。overrides 是 {'sampler.shift': 5.5} 这种点号路径。"""
cfg = copy.deepcopy(DEFAULTS)
_deep_merge(cfg, _read_layer("default"))
_deep_merge(cfg, _read_layer("local"))
_deep_merge(cfg, _env_overrides())
if overrides:
for path, val in overrides.items():
if val is None:
continue
_set(cfg, path, val)
return cfg
def _set(cfg, path, val):
keys = path.split(".")
node = cfg
for k in keys[:-1]:
node = node.setdefault(k, {})
node[keys[-1]] = val
_ENV_MAP = {
"SONGFORGE_SERVER": "engine.server",
"SONGFORGE_TIMEOUT": "engine.timeout_sec",
"SONGFORGE_CHECKPOINT": "model.checkpoint",
"SONGFORGE_LORA": "model.lora",
"SONGFORGE_LORA_STRENGTH": "model.lora_model_strength",
"SONGFORGE_SHIFT": "sampler.shift",
"SONGFORGE_STEPS": "sampler.steps",
"SONGFORGE_CFG": "sampler.cfg",
"SONGFORGE_ENC_CFG": "encode.cfg_scale",
"SONGFORGE_TEMPERATURE": "encode.temperature",
"SONGFORGE_TOP_P": "encode.top_p",
"SONGFORGE_TOP_K": "encode.top_k",
"SONGFORGE_MIN_P": "encode.min_p",
"SONGFORGE_TEMPLATE": "paths.workflow_template",
"SONGFORGE_RUNS": "paths.runs_dir",
"SONGFORGE_TMP": "paths.tmp_dir",
"SONGFORGE_LYRICS_DIR": "paths.lyrics_dir",
"SONGFORGE_QC_CACHE": "paths.qc_cache_dir",
"SONGFORGE_STYLE_CACHE": "paths.style_cache_dir",
"SONGFORGE_OUTPUT_PREFIX": "paths.output_prefix",
"SONGFORGE_LANGUAGE": "song.language",
"SONGFORGE_COMFY_ROOT": "paths.comfy_root",
"SONGFORGE_QC_PYTHON": "paths.qc_python",
"SONGFORGE_MUSIC_DIR": "paths.music_dir",
}
_NUMERIC = {"engine.timeout_sec", "model.lora_model_strength",
"model.lora_clip_strength", "sampler.shift", "sampler.steps",
"sampler.cfg", "sampler.denoise", "encode.cfg_scale",
"encode.temperature", "encode.top_p", "encode.top_k",
"encode.min_p", "lyrics.sing_bar_ratio", "lyrics.intro_bars",
"lyrics.syllable_per_bar_min", "lyrics.syllable_per_bar_max",
"lyrics.line_syllable_max"}
def _env_overrides():
out = {}
for env_key, path in _ENV_MAP.items():
raw = os.environ.get(env_key)
if raw is None or raw == "":
continue
if path in _NUMERIC:
try:
raw = float(raw)
if raw.is_integer() and path not in ("sampler.shift",
"sampler.cfg",
"encode.cfg_scale",
"encode.temperature",
"encode.top_p",
"encode.min_p",
"lyrics.sing_bar_ratio",
"model.lora_model_strength",
"model.lora_clip_strength"):
raw = int(raw)
except ValueError:
continue
elif raw.lower() in ("true", "false"):
raw = raw.lower() == "true"
node = out
keys = path.split(".")
for k in keys[:-1]:
node = node.setdefault(k, {})
node[keys[-1]] = raw
return out
def styles():
return _read_json("styles.json")
def lexicon():
return _read_json("lexicon.json")
def baseline_path(name):
"""config/baseline/<name> 绝对路径。"""
return os.path.join(CONFIG_DIR, "baseline", name)
def python_hint():
"""当前解释器信息(doctor 用)。"""
return "%s (%s)" % (sys.executable, sys.version.split()[0])