[New Model] Add TADA (Hume AI) TTS model support · vllm-project/vllm-omni#2001

(8 comments) (0 reactions) (1 assignee)Python (1.067 forks)github user discovery

good first issuehelp wantednew model

Métricas do repositório

Stars: (4.990 stars)
Métricas de merge de PR: (Métricas PR pendentes)

Description

Model

TADA by Hume AI — a speech-language model that unifies speech synthesis with text generation using 1:1 text-speech token alignment built on Llama 3.2.

Architecture

Encoder (HumeAI/tada-codec): encodes reference audio into aligned token sequences
LLM (TadaForCausalLM): autoregressive generation, available in 1B and 3B-ML (multilingual) variants
Generates the complete speech segment per text token in a single AR step (dynamic duration/prosody)

This would likely be a 2-stage pipeline in vllm-omni (AR generation → codec decode), similar to Qwen3 TTS / Fish Speech.

References

GitHub: https://github.com/HumeAI/tada
Requested in https://github.com/vllm-project/vllm-omni/issues/1795#issuecomment-4048885352

cc @ashok-arora — would you be interested in taking a look at this?

Guia do colaborador

Direção de pesquisa: Examine os padrões de integração de modelos existentes no vllm omni (ex.: Qwen3 TTS, Fish Speech) para entender a estrutura de pipeline esperada. Em seguida, implemente o modelo TADA como um pipeline de dois estágios: geração AR seguida de decodificação de codec, semelhante a esses exemplos.
Pilha de tecnologia: python
Domain: aibackend
Tipo Issue: Funcionalidade
Difficulty: 4
Tempo estimado: Mais de 1 semana
Status da atividade: Ativo
Clarity: Principalmente claro
Prerequisites: PythonPyTorch
Simpatia para novatos: 20