utils

Time formatting utilities for VAD alignment display

Time Formatting

format_time_precise


def format_time_precise(
    seconds:Optional, # Time in seconds
)->str: # Formatted time string (m:ss.s)

Format seconds as m:ss.s for sub-second display.

Tests

Audio File Boundaries

source

get_audio_file_boundaries


def get_audio_file_boundaries(
    chunks:List, # Ordered list of VAD chunks
)->Set: # Indices where audio_file_index changes from the previous chunk

Find indices where audio_file_index changes between adjacent chunks.

A boundary at index N means chunk[N].audio_file_index differs from chunk[N-1].audio_file_index.

source

get_audio_file_count


def get_audio_file_count(
    chunks:List, # Ordered list of VAD chunks
)->int: # Number of unique audio files

Count the number of unique audio files in the chunk list.

source

get_audio_file_position


def get_audio_file_position(
    chunks:List, # Ordered list of VAD chunks
    focused_index:int, # Index of the focused chunk
)->Optional: # 1-based position of the audio file, or None

Get the audio file position (1-based) of the focused chunk.

Returns which audio file the focused chunk belongs to, based on order of first appearance.

assert format_time_precise(6.6) == "0:06.6"
assert format_time_precise(9.8) == "0:09.8"
assert format_time_precise(65.25) == "1:05.2"
assert format_time_precise(0.0) == "0:00.0"
assert format_time_precise(None) == "-:--.-"
print("format_time_precise tests passed")

from cjm_transcript_vad_align.models import VADChunk

# Test get_audio_file_boundaries
chunks_single = [
    VADChunk(index=0, start_time=0.0, end_time=1.0, audio_file_index=0),
    VADChunk(index=1, start_time=1.0, end_time=2.0, audio_file_index=0),
]
assert get_audio_file_boundaries(chunks_single) == set()

chunks_multi = [
    VADChunk(index=0, start_time=0.0, end_time=1.0, audio_file_index=0),
    VADChunk(index=1, start_time=1.0, end_time=2.0, audio_file_index=0),
    VADChunk(index=2, start_time=0.0, end_time=1.5, audio_file_index=1),
    VADChunk(index=3, start_time=1.5, end_time=3.0, audio_file_index=1),
    VADChunk(index=4, start_time=0.0, end_time=2.0, audio_file_index=2),
]
assert get_audio_file_boundaries(chunks_multi) == {2, 4}
assert get_audio_file_boundaries([]) == set()
print("get_audio_file_boundaries tests passed")

# Test get_audio_file_count
assert get_audio_file_count(chunks_single) == 1
assert get_audio_file_count(chunks_multi) == 3
assert get_audio_file_count([]) == 0
print("get_audio_file_count tests passed")

# Test get_audio_file_position
assert get_audio_file_position(chunks_multi, 0) == 1
assert get_audio_file_position(chunks_multi, 1) == 1
assert get_audio_file_position(chunks_multi, 2) == 2
assert get_audio_file_position(chunks_multi, 4) == 3
assert get_audio_file_position(chunks_multi, 99) is None
assert get_audio_file_position([], 0) is None
print("get_audio_file_position tests passed")

get_audio_file_boundaries tests passed
get_audio_file_count tests passed
get_audio_file_position tests passed