mltk.utils.audio_dataset_generator.GenerationConfig

class GenerationConfig

Audio sample generation configuration

Properties

keyword	The keyword text (this is either the base keyword or keyword alias)
keyword_group	The base keyword
voice	The backend voice
rate	The speaking rate
pitch	The voice pitch

Methods

__init__
copy	Return a deep copy of the configuration

voice: Voice

The backend voice

rate: VoiceRate

The speaking rate

pitch: VoicePitch

The voice pitch

keyword: str = None

The keyword text (this is either the base keyword or keyword alias)

keyword_group: str = None

The base keyword

copy()

Return a deep copy of the configuration

Return type:

GenerationConfig

__init__(voice, rate, pitch, keyword=None, keyword_group=None)

Parameters:

• voice (Voice) –

• rate (VoiceRate) –

• pitch (VoicePitch) –

• keyword (str) –

• keyword_group (str) –

Return type:

None