Travis Vasceannie
af1285b181
- Introduced .python-version for Python version management. - Added AGENTS.md for documentation on agent usage and best practices. - Created alembic.ini for database migration configurations. - Implemented main.py as the entry point for the application. - Established pyproject.toml for project dependencies and configurations. - Initialized README.md for project overview. - Generated uv.lock for dependency locking. - Documented milestones and specifications in docs/milestones.md and docs/spec.md. - Created logs/status_line.json for logging status information. - Added initial spike implementations for UI tray hotkeys, audio capture, ASR latency, and encryption validation. - Set up NoteFlow core structure in src/noteflow with necessary modules and services. - Developed test suite in tests directory for application, domain, infrastructure, and integration testing. - Included initial migration scripts in infrastructure/persistence/migrations for database setup. - Established security protocols in infrastructure/security for key management and encryption. - Implemented audio infrastructure for capturing and processing audio data. - Created converters for ASR and ORM in infrastructure/converters. - Added export functionality for different formats in infrastructure/export. - Ensured all new files are included in the repository for future development.
89 lines
2.4 KiB
Python
89 lines
2.4 KiB
Python
"""Data Transfer Objects for ASR.
|
|
|
|
These DTOs define the data structures used by ASR components.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from typing import NewType
|
|
|
|
SegmentID = NewType("SegmentID", str)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class WordTiming:
|
|
"""Word-level timing information."""
|
|
|
|
word: str
|
|
start: float # Start time in seconds
|
|
end: float # End time in seconds
|
|
probability: float # Confidence (0.0-1.0)
|
|
|
|
def __post_init__(self) -> None:
|
|
"""Validate timing data."""
|
|
if self.end < self.start:
|
|
raise ValueError(f"Word end ({self.end}) < start ({self.start})")
|
|
if not 0.0 <= self.probability <= 1.0:
|
|
raise ValueError(f"Probability must be 0.0-1.0, got {self.probability}")
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class AsrResult:
|
|
"""ASR transcription result for a segment."""
|
|
|
|
text: str
|
|
start: float # Start time in seconds
|
|
end: float # End time in seconds
|
|
words: tuple[WordTiming, ...] = field(default_factory=tuple)
|
|
language: str = "en"
|
|
language_probability: float = 1.0
|
|
avg_logprob: float = 0.0
|
|
no_speech_prob: float = 0.0
|
|
|
|
def __post_init__(self) -> None:
|
|
"""Validate result data."""
|
|
if self.end < self.start:
|
|
raise ValueError(f"Segment end ({self.end}) < start ({self.start})")
|
|
|
|
@property
|
|
def duration(self) -> float:
|
|
"""Duration of the segment in seconds."""
|
|
return self.end - self.start
|
|
|
|
|
|
@dataclass
|
|
class PartialUpdate:
|
|
"""Unstable partial transcript (may be replaced)."""
|
|
|
|
text: str
|
|
start: float
|
|
end: float
|
|
|
|
def __post_init__(self) -> None:
|
|
"""Validate partial data."""
|
|
if self.end < self.start:
|
|
raise ValueError(f"Partial end ({self.end}) < start ({self.start})")
|
|
|
|
|
|
@dataclass
|
|
class FinalSegment:
|
|
"""Committed transcript segment (immutable after creation)."""
|
|
|
|
segment_id: SegmentID
|
|
text: str
|
|
start: float
|
|
end: float
|
|
words: tuple[WordTiming, ...] = field(default_factory=tuple)
|
|
speaker_label: str = "Unknown"
|
|
|
|
def __post_init__(self) -> None:
|
|
"""Validate segment data."""
|
|
if self.end < self.start:
|
|
raise ValueError(f"Segment end ({self.end}) < start ({self.start})")
|
|
|
|
@property
|
|
def duration(self) -> float:
|
|
"""Duration of the segment in seconds."""
|
|
return self.end - self.start
|