Module tts_executor 

Qwen3-TTS Executor — text-to-speech pipeline wiring Talker LM + Vocoder.

Implements: text tokenization, autoregressive codec token generation, SubTalker code prediction (TODO), vocoder waveform synthesis.

Structs

TtsModelExecutor

Qwen3-TTS executor: text-to-speech synthesis.

Functions

sample_token

Sample a token from logits with temperature, top-k, and repetition penalty. Sample a token matching qwen3-tts-rs reference: