feat(moss-tts-nano): add online serving, Gradio demo, and fix /v1/audio/speech integration
- Register moss_tts_nano as TTS model stage in serving_speech.py (model detection, validation, prompt building) - Fix registry mod_relname: moss_tts_nano -> modeling_moss_tts_nano - Fix stage config: is_comprehension=true (required for generate task) - Fix default mode: voice_clone -> continuation (built-in presets) - Add compute_logits stub for VllmModelForTextGeneration protocol - Remove unused _sentinel nn.Parameter - Add Gradio demo with AudioWorklet streaming player (48kHz stereo) - Add online/offline serving docs and launch scripts TODO: Single-stage generation models don't support true streaming (progressive audio chunks). Current TTFP = full generation time. Needs multi-step scheduling support in GPUGenerationModelRunner. Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
1 parent
571c8d4235
commit
fc81b8504a
9 files changed
+1065
-6
No files matched your search
@@ -93,7 +93,7 @@ _DEFAULT_AUDIO_TOP_K = 25
|
||||
_DEFAULT_AUDIO_REPETITION_PENALTY = 1.2
|
||||
_DEFAULT_MAX_NEW_FRAMES = 375
|
||||
_DEFAULT_VOICE = "Junhao"
|
||||
_DEFAULT_MODE = "voice_clone"
|
||||
_DEFAULT_MODE = "continuation"
|
||||
|
||||
|
||||
def _pick(info: dict, key: str, default):
|
||||
@@ -149,9 +149,6 @@ class MossTTSNanoForGeneration(nn.Module):
|
||||
self._device: torch.device | None = None
|
||||
self._lock = threading.Lock()
|
||||
|
||||
# Dummy parameter so vLLM can resolve the device via next(parameters()).
|
||||
self._sentinel = nn.Parameter(torch.zeros(1), requires_grad=False)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Weight loading
|
||||
# ------------------------------------------------------------------
|
||||
@@ -405,6 +402,13 @@ class MossTTSNanoForGeneration(nn.Module):
|
||||
# vLLM boilerplate: embed_input_ids required by generation runner
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def compute_logits(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
) -> torch.Tensor | None:
|
||||
# Generation stage does not produce logits; satisfy VllmModelForTextGeneration protocol.
|
||||
return None
|
||||
|
||||
def embed_input_ids(
|
||||
self,
|
||||
input_ids: torch.Tensor,
|
||||
|
||||
@@ -166,7 +166,7 @@ _OMNI_MODELS = {
|
||||
## MOSS-TTS-Nano
|
||||
"MossTTSNanoForCausalLM": (
|
||||
"moss_tts_nano",
|
||||
"moss_tts_nano",
|
||||
"modeling_moss_tts_nano",
|
||||
"MossTTSNanoForGeneration",
|
||||
),
|
||||
"DyninOmniForConditionalGeneration": (
|
||||
|
||||
Reference in new issue
Block a user