[Model] Add Ming-omni-tts dense 0.5B pipeline (#2906)

Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
akshatvishuandHongsheng Liu authored and GitHub committed 2026-06-10 20:11:04 +08:00
1 parent 39ae6e12f8
commit 2fa4c7a4a9
55 files changed
+6263 -549

No files matched your search

+61 -5
View File
@@ -7,6 +7,43 @@ from pydantic import AliasChoices, BaseModel, Field, field_validator, model_vali
_MAX_EMBEDDING_DIM = 8192
def _normalize_ref_audio_value(value):
if value is None:
return None
if isinstance(value, str):
return value
if isinstance(value, (list, tuple)):
items = []
for item in value:
if not isinstance(item, str):
raise TypeError("'ref_audio' list entries must be strings")
items.append(item)
if not items:
raise ValueError("'ref_audio' list cannot be empty")
return items
raise TypeError("'ref_audio' must be a string or list of strings")
def _normalize_speaker_embedding_value(value):
if value is None:
return None
if not isinstance(value, (list, tuple)):
raise TypeError("'speaker_embedding' must be a list of numbers or list of embedding vectors")
if not value:
return []
first = value[0]
if isinstance(first, (list, tuple)):
embeddings = []
for item in value:
if not isinstance(item, (list, tuple)):
raise TypeError("'speaker_embedding' must not mix flat and nested values")
embeddings.append([float(x) for x in item])
return embeddings
return [float(x) for x in value]
class OpenAICreateSpeechRequest(BaseModel):
input: str
model: str | None = None
@@ -46,7 +83,7 @@ class OpenAICreateSpeechRequest(BaseModel):
default=None,
description="Language code (e.g., 'Chinese', 'English', 'Auto')",
)
ref_audio: str | None = Field(
ref_audio: str | list[str] | None = Field(
default=None,
description="Reference audio for voice cloning (Base task). URL, base64, or file URI.",
)
@@ -73,7 +110,7 @@ class OpenAICreateSpeechRequest(BaseModel):
default=None,
description="Use speaker embedding only without in-context learning (Base task)",
)
speaker_embedding: list[float] | None = Field(
speaker_embedding: list[float] | list[list[float]] | None = Field(
default=None,
max_length=_MAX_EMBEDDING_DIM,
description="Pre-computed speaker embedding vector (1024-dim for 0.6B, "
@@ -108,10 +145,29 @@ class OpenAICreateSpeechRequest(BaseModel):
raise ValueError("'sse' is not a supported stream_format yet. Please use 'audio'.")
return v
@field_validator("ref_audio", mode="before")
@classmethod
def normalize_ref_audio(cls, v):
return _normalize_ref_audio_value(v)
@field_validator("speaker_embedding")
@classmethod
def validate_speaker_embedding(cls, v: list[float] | None) -> list[float] | None:
if v is not None and not all(math.isfinite(x) for x in v):
def validate_speaker_embedding(
cls, v: list[float] | list[list[float]] | None
) -> list[float] | list[list[float]] | None:
v = _normalize_speaker_embedding_value(v)
if v is None:
return None
if not v:
return []
if isinstance(v[0], list):
for item in v:
if not item:
raise ValueError("'speaker_embedding' nested vectors must be non-empty")
if not all(math.isfinite(x) for x in item):
raise ValueError("'speaker_embedding' values must be finite (no NaN or Inf)")
return v
if not all(math.isfinite(x) for x in v):
raise ValueError("'speaker_embedding' values must be finite (no NaN or Inf)")
return v
@@ -210,7 +266,7 @@ class OpenAICreateSpeechRequest(BaseModel):
@model_validator(mode="after")
def validate_embedding_constraints(self) -> "OpenAICreateSpeechRequest":
if self.speaker_embedding is not None:
if self.ref_audio is not None:
if self.ref_audio is not None and not isinstance(self.ref_audio, list):
raise ValueError("'speaker_embedding' and 'ref_audio' are mutually exclusive")
return self