t3_inference

Run T3 inference to generate speech tokens

Description

Run T3 inference to generate speech tokens

Usage

t3_inference(
  model,
  cond,
  text_tokens,
  max_new_tokens = 1000,
  temperature = 0.8,
  cfg_weight = 0.5,
  top_p = 0.95,
  min_p = 0.05,
  repetition_penalty = 1.2
)

Arguments

  • model: T3 model
  • cond: T3 conditioning
  • text_tokens: Tokenized text (tensor)
  • max_new_tokens: Maximum speech tokens to generate
  • temperature: Sampling temperature
  • cfg_weight: Classifier-free guidance weight
  • top_p: Nucleus sampling threshold
  • min_p: Minimum probability threshold
  • repetition_penalty: Repetition penalty

Value

Generated speech tokens