vllm_omni.model_executor.models.ming_tts ¶

Modules:

Name	Description
`aggregator`
`audio_prep`
`config_ming_tts`	Ming dense checkpoint config adapters.
`constants`
`flowloss_head`
`fm`
`ming_tts`
`ming_tts_audio_vae`
`ming_tts_llm`
`patch_emission`
`pipeline`	Ming TTS pipeline: Stage-0 LLM+flow -> Stage-1 audio VAE.
`prompt_assembly`
`prompt_encoder`
`speaker_extractor`
`validation`