tflite_support.task.audio.AudioEmbedder

View source on GitHub

Class that performs dense feature vector extraction on audio.

tflite_support.task.audio.AudioEmbedder(
    options: tflite_support.task.audio.AudioEmbedderOptions,
    cpp_embedder: _CppAudioEmbedder
) -> None

Attributes
number_of_output_layers	Gets the number of output layers of the model.
required_audio_format	Gets the required audio format for the model.
required_input_buffer_size	Gets the required input buffer size for the model.

Methods

cosine_similarity

View source

cosine_similarity(
    u: tflite_support.task.processor.FeatureVector,
    v: tflite_support.task.processor.FeatureVector
) -> float

Computes cosine similarity [1] between two feature vectors.

create_audio_record

View source

create_audio_record() -> tflite_support.task.audio.AudioRecord

Creates an AudioRecord instance to record audio.

Returns
An AudioRecord instance.

create_from_file

View source

@classmethod
create_from_file(
    file_path: str
) -> 'AudioEmbedder'

Creates the AudioEmbedder object from a TensorFlow Lite model.

Args
file_path	Path to the model.

Returns
AudioEmbedder object that's created from options.

Raises
ValueError	If failed to create AudioEmbedder object from the provided file such as invalid file.
RuntimeError	If other types of error occurred.

create_from_options

View source

@classmethod
create_from_options(
    options: tflite_support.task.audio.AudioEmbedderOptions
) -> 'AudioEmbedder'

Creates the AudioEmbedder object from audio embedder options.

Args
options	Options for the audio embedder task.

Returns
AudioEmbedder object that's created from options.

Raises
ValueError	If failed to create AudioEmbedder object from AudioEmbedderOptions such as missing the model.
RuntimeError	If other types of error occurred.

create_input_tensor_audio

View source

create_input_tensor_audio() -> tflite_support.task.audio.TensorAudio

Creates a TensorAudio instance to store the audio input.

Returns
A TensorAudio instance.

embed

View source

embed(
    audio: tflite_support.task.audio.TensorAudio
) -> tflite_support.task.processor.EmbeddingResult

Performs actual feature vector extraction on the provided audio.

Args
audio	Tensor audio, used to extract the feature vectors.

Returns
embedding result.

Raises
ValueError	If any of the input arguments is invalid.
RuntimeError	If failed to calculate the embedding vector.

get_embedding_dimension

View source

get_embedding_dimension(
    output_index: int
) -> int

Gets the dimensionality of the embedding output.

Args
output_index	The output index of output layer.

Returns
Dimensionality of the embedding output by the output_index'th output layer. Returns -1 if output_index is out of bounds.