Vllm.Config.SpeechToTextConfig (VLLM v0.3.0)

Configuration for speech-to-text models.

Summary

t()

Constructs SpeechToTextConfig.

sample_rate(ref)

@opaque t()

@spec allow_audio_chunking(SnakeBridge.Ref.t()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

@spec max_audio_clip_s(SnakeBridge.Ref.t()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

@spec min_energy_split_window_size(SnakeBridge.Ref.t()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

@spec new(term(), term(), term(), keyword()) ::
  {:ok, SnakeBridge.Ref.t()} | {:error, Snakepit.Error.t()}

Constructs SpeechToTextConfig.

@spec overlap_chunk_second(SnakeBridge.Ref.t()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

@spec sample_rate(SnakeBridge.Ref.t()) :: {:ok, term()} | {:error, Snakepit.Error.t()}