mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 21:00:42 -07:00
James PineandClaude Opus 4.7
87c582ad54
Ships the Capture release end to end. Global-hotkey dictation with synthetic paste into the focused app on macOS and Windows, an on-screen pill across recording / transcribing / refining, customizable push-to- talk and toggle chords, and an accessibility-permission prompt scoped to Settings → Captures with inline re-check feedback. Voice profiles gain optional personalities that power compose / rewrite / respond actions via a local Qwen3 LLM — shared with refinement, so there is one local LLM in the app, not two. Refinement hardened with deterministic Whisper-loop collapse before the LLM sees the transcript, per-capture flag snapshots for re-runs, and a ten-transcript evaluation harness across every bundled refinement size. Version bump 0.4.5 → 0.5.0. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
141 lines
3.8 KiB
Python
141 lines
3.8 KiB
Python
"""
|
|
Configuration module for voicebox backend.
|
|
|
|
Handles data directory configuration for production bundling.
|
|
"""
|
|
|
|
import logging
|
|
import os
|
|
from pathlib import Path
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# Allow users to override the HuggingFace model download directory.
|
|
# Set VOICEBOX_MODELS_DIR to an absolute path before starting the server.
|
|
# This sets HF_HUB_CACHE so all huggingface_hub downloads go to that path.
|
|
_custom_models_dir = os.environ.get("VOICEBOX_MODELS_DIR")
|
|
if _custom_models_dir:
|
|
os.environ["HF_HUB_CACHE"] = _custom_models_dir
|
|
logger.info("Model download path set to: %s", _custom_models_dir)
|
|
|
|
# Default data directory (used in development)
|
|
_data_dir = Path("data").resolve()
|
|
|
|
|
|
def _path_relative_to_any_data_dir(path: Path) -> Path | None:
|
|
"""Extract the path within a data dir from an absolute or relative path."""
|
|
parts = path.parts
|
|
for idx, part in enumerate(parts):
|
|
if part != "data":
|
|
continue
|
|
|
|
tail = parts[idx + 1 :]
|
|
if tail:
|
|
return Path(*tail)
|
|
return Path()
|
|
|
|
return None
|
|
|
|
|
|
def set_data_dir(path: str | Path):
|
|
"""
|
|
Set the data directory path.
|
|
|
|
Args:
|
|
path: Path to the data directory
|
|
"""
|
|
global _data_dir
|
|
_data_dir = Path(path).resolve()
|
|
_data_dir.mkdir(parents=True, exist_ok=True)
|
|
logger.info("Data directory set to: %s", _data_dir)
|
|
|
|
|
|
def get_data_dir() -> Path:
|
|
"""
|
|
Get the data directory path.
|
|
|
|
Returns:
|
|
Path to the data directory
|
|
"""
|
|
return _data_dir
|
|
|
|
|
|
def to_storage_path(path: str | Path) -> str:
|
|
"""Convert a filesystem path to a DB-safe path relative to the data dir."""
|
|
resolved_path = Path(path).resolve()
|
|
|
|
relative_to_any_data_dir = _path_relative_to_any_data_dir(resolved_path)
|
|
if relative_to_any_data_dir is not None:
|
|
return str(relative_to_any_data_dir)
|
|
|
|
try:
|
|
return str(resolved_path.relative_to(_data_dir))
|
|
except ValueError:
|
|
return str(resolved_path)
|
|
|
|
|
|
def resolve_storage_path(path: str | Path | None) -> Path | None:
|
|
"""Resolve a DB-stored path against the configured data dir."""
|
|
if path is None:
|
|
return None
|
|
|
|
stored_path = Path(path)
|
|
if stored_path.is_absolute():
|
|
rebased_path = _path_relative_to_any_data_dir(stored_path)
|
|
if rebased_path is not None:
|
|
candidate = (_data_dir / rebased_path).resolve()
|
|
if candidate.exists() or not stored_path.exists():
|
|
return candidate
|
|
|
|
return stored_path
|
|
|
|
# 0.3.0 records sometimes stored relative paths with the data-dir name
|
|
# baked in (e.g. "data/profiles/..."). Joining those directly with
|
|
# _data_dir produces a spurious "<data_dir>/data/profiles/..." nest.
|
|
if stored_path.parts and stored_path.parts[0] == "data":
|
|
stored_path = (
|
|
Path(*stored_path.parts[1:]) if len(stored_path.parts) > 1 else Path()
|
|
)
|
|
|
|
return (_data_dir / stored_path).resolve()
|
|
|
|
|
|
def get_db_path() -> Path:
|
|
"""Get database file path."""
|
|
return _data_dir / "voicebox.db"
|
|
|
|
|
|
def get_profiles_dir() -> Path:
|
|
"""Get profiles directory path."""
|
|
path = _data_dir / "profiles"
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|
|
|
|
|
|
def get_generations_dir() -> Path:
|
|
"""Get generations directory path."""
|
|
path = _data_dir / "generations"
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|
|
|
|
|
|
def get_captures_dir() -> Path:
|
|
"""Get captures directory path."""
|
|
path = _data_dir / "captures"
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|
|
|
|
|
|
def get_cache_dir() -> Path:
|
|
"""Get cache directory path."""
|
|
path = _data_dir / "cache"
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|
|
|
|
|
|
def get_models_dir() -> Path:
|
|
"""Get models directory path."""
|
|
path = _data_dir / "models"
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|