VoxRtcServer.SpeechContextSoundSpan (vox_rtc_server v0.2.4)

Copy Markdown View Source

A timestamped YAMNet sound span with its peak model score.

Summary

Types

t()

Types

t()

@type t() :: %VoxRtcServer.SpeechContextSoundSpan{
  end_ms: pos_integer(),
  label: String.t(),
  score: float(),
  start_ms: non_neg_integer()
}