[Model] Add Breeze-TTS-2 two-stage AR TTS support (talker + codec, streaming) (#7084)

Signed-off-by: noname <liuzhiwei08@kuaishou.com>
Signed-off-by: noname <133508552+lzwnoname@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: noname <liuzhiwei08@kuaishou.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>

tests/entrypoints/openai_api/test_tts_adapter.py

@@ -65,6 +65,7 @@ EXPECTED_MODEL_TYPES = {
     "higgs_audio_v2",
     "higgs_audio_v3",
     "glm_tts",
+    "breeze_tts_2",
     "step_audio2",
     "indextts2",
     "indextts2_5",

tests/entrypoints/openai_api/test_tts_detection.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 """TTS model detection: registry-driven stage -> model-type resolution.
 
 ``serving_speech.py`` used to carry a hand-written 20-branch ladder mapping
@@ -138,6 +139,7 @@ _PIPELINE_STAGES = [
     "audio_tokenizer",
     "audio_vae",
     "aura",
+    "breeze_tts_2",
     "code2wav",
     "cosyvoice3_code2wav",
     "cosyvoice3_talker",
@@ -184,6 +186,7 @@ _STAGES = [*_PIPELINE_STAGES, None, "vae", "not_a_real_stage"]
 _ARCHS = [
     None,
     "VoxCPM2TalkerForConditionalGeneration",
+    "BreezeForConditionalGeneration",
     "MingTTSForConditionalGeneration",
     "CovoAudioForConditionalGeneration",
     "MyCovoAudioThing",