File size: 2,597 Bytes
af4851b cd0ff97 af4851b cd0ff97 af4851b cd0ff97 af4851b cd0ff97 af4851b cd0ff97 af4851b cd0ff97 af4851b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | from dataclasses import asdict, dataclass, field
from pathlib import Path
from typing import Any, Dict, List, Optional
from backend.synthesis_catalog import LOCAL_BACKEND, OMNIVOICE_MODEL
JsonDict = Dict[str, Any]
@dataclass
class Chapter:
id: str
label: str
title: str
text: str
chars: int
est_minutes: int
included: bool = True
start_seconds: int = 0
def to_dict(self) -> JsonDict:
data = asdict(self)
data["n"] = data["label"]
return data
@dataclass
class SessionRecord:
session_id: str
root: Path
created_at: float
touched_at: float
@dataclass
class VoiceConfig:
mode: str = "auto"
model: str = OMNIVOICE_MODEL
backend: str = LOCAL_BACKEND
narrator_id: Optional[str] = None
sample_path: Optional[str] = None
reference_text: Optional[str] = None
design_prompt: Optional[str] = None
speaker: Optional[str] = None
language: Optional[str] = None
apply_text_normalization: bool = False
@classmethod
def from_dict(cls, data: JsonDict) -> "VoiceConfig":
return cls(
mode=data.get("mode", "auto"),
model=data.get("model", OMNIVOICE_MODEL),
backend=data.get("backend", LOCAL_BACKEND),
narrator_id=data.get("narratorId") or data.get("narrator_id"),
sample_path=data.get("samplePath") or data.get("sample_path"),
reference_text=data.get("referenceText") or data.get("reference_text"),
design_prompt=data.get("designPrompt") or data.get("design_prompt"),
speaker=data.get("speaker"),
language=data.get("language"),
apply_text_normalization=bool(
data.get("applyTextNormalization", data.get("apply_text_normalization", False))
),
)
def to_dict(self) -> JsonDict:
return {
"mode": self.mode,
"model": self.model,
"backend": self.backend,
"narratorId": self.narrator_id,
"samplePath": self.sample_path,
"referenceText": self.reference_text,
"designPrompt": self.design_prompt,
"speaker": self.speaker,
"language": self.language,
"applyTextNormalization": self.apply_text_normalization,
}
@dataclass
class RenderArtifact:
path: Path
duration_seconds: int
chapter_id: str
@dataclass
class RenderJob:
session_id: str
status: str = "idle"
current_chapter_id: Optional[str] = None
outputs: List[RenderArtifact] = field(default_factory=list)
|