Options for the audio embedder task.
mp.tasks.audio.AudioEmbedderOptions(
base_options: mp.tasks.BaseOptions
,
running_mode: mp.tasks.audio.RunningMode
= mp.tasks.audio.AudioClassifierOptions.running_mode
,
l2_normalize: Optional[bool] = None,
quantize: Optional[bool] = None,
result_callback: Optional[Callable[[AudioEmbedderResult, int], None]] = None
)
Attributes |
base_options
|
Base options for the audio embedder task.
|
running_mode
|
The running mode of the task. Default to the audio clips mode.
Audio embedder task has two running modes: 1) The audio clips mode for
running embedding extraction on independent audio clips. 2) The audio
stream mode for running embedding extraction on the audio stream, such as
from microphone. In this mode, the "result_callback" below must be
specified to receive the embedding results asynchronously.
|
l2_normalize
|
Whether to normalize the returned feature vector with L2 norm.
Use this option only if the model does not already contain a native
L2_NORMALIZATION TF Lite Op. In most cases, this is already the case and
L2 norm is thus achieved through TF Lite inference.
|
quantize
|
Whether the returned embedding should be quantized to bytes via
scalar quantization. Embeddings are implicitly assumed to be unit-norm and
therefore any dimension is guaranteed to have a value in [-1.0, 1.0]. Use
the l2_normalize option if this is not the case.
|
result_callback
|
The user-defined result callback for processing audio
stream data. The result callback should only be specified when the running
mode is set to the audio stream mode.
|
Methods
__eq__
__eq__(
other
)
Class Variables |
l2_normalize
|
None
|
quantize
|
None
|
result_callback
|
None
|
running_mode
|
<AudioTaskRunningMode.AUDIO_CLIPS: 'AUDIO_CLIPS'>
|