neuralset.events.etypes.Audio¶

pydantic model neuralset.events.etypes.Audio[source][source]¶

Audio event corresponding to a WAV file.

Requires soundfile to be installed. Duration and frequency are auto-detected from the file if not provided.

Returns:: Audio tensor of shape (num_samples, num_channels) when read() is called
Return type:: torch.Tensor

Notes

Automatically detects frequency and duration from file metadata
Supports partial loading via offset and duration
Mono audio is automatically reshaped to (N, 1)

Examples

audio = Audio(start=0, timeline="audio_exp", filepath="speech.wav")
audio_tensor = audio.read()  # Returns torch.Tensor
print(audio_tensor.shape)  # (num_samples, num_channels)

Fields:

requirements: ClassVar[tuple[str, ...]] = ('soundfile',)[source]¶

type: tp.ClassVar[str] = 'Audio'[source]¶

← Back to API reference