constants.py

"""TranscribeX constants and data models."""
from __future__ import annotations

from dataclasses import dataclass
from typing import List, Optional

# ── App metadata ──────────────────────────────────────────────
APP_TITLE = "TranscribeX - Media to TXT/DOCX/SRT/VTT"
APP_VERSION = "1.2"
MIN_WIDTH = 760

# ── Transcription defaults ────────────────────────────────────
BEAM_SIZE = 5
BEST_OF = 5
VAD_MIN_SILENCE_MS = 500

# ── DOCX formatting ──────────────────────────────────────────
DOCX_META_FONT_SIZE_PT = 9
DOCX_PARAGRAPH_SPACING_PT = 6

# ── Dropdown options ─────────────────────────────────────────
MODEL_SIZES = ["tiny", "base", "small", "medium", "large-v3"]
COMPUTE_TYPES_GPU = ["int8", "int8_float16", "float16", "float32"]
COMPUTE_TYPES_CPU = ["int8", "float32"]
OUTPUT_FORMATS = ["txt", "docx", "srt", "vtt"]

LANGUAGES = [
    "Auto-detect",
    "en", "es", "fr", "de", "it", "pt", "nl", "ru", "zh",
    "ja", "ko", "ar", "hi", "pl", "uk", "cs", "sv", "da",
    "fi", "no", "tr", "vi", "th", "id", "ms", "he", "el",
    "ro", "hu", "bg", "hr", "sk", "sl", "lt", "lv", "et",
    "sr", "ca", "gl", "eu",
]

# ── File filters ─────────────────────────────────────────────
ALLOWED_EXTENSIONS = {
    ".mp3", ".mp4", ".m4a", ".wav", ".flac",
    ".aac", ".ogg", ".wma", ".mov", ".webm", ".mkv",
}
FILE_DIALOG_FILTER = (
    "Media Files (*.mp3 *.mp4 *.m4a *.wav *.flac *.aac *.ogg *.wma *.mov *.webm *.mkv);;"
    "All Files (*)"
)

# ── Batch warning threshold ──────────────────────────────────
LARGE_BATCH_THRESHOLD = 10
SLOW_MODELS = {"medium", "large-v3"}

# ── Defaults ─────────────────────────────────────────────────
DEFAULT_MODEL = "small"
DEFAULT_COMPUTE = "int8"
DEFAULT_FORMAT = "txt"
DEFAULT_LANGUAGE = "Auto-detect"


@dataclass
class TranscribeJob:
    files: List[str]
    out_dir: str
    model_size: str
    out_format: str
    add_timestamps: bool
    language: Optional[str]
    compute_type: str
    use_vad: bool
    use_gpu: bool