191 lines
9.2 KiB
Python
191 lines
9.2 KiB
Python
"""回归用例:音频模型不许有「mac 本地」,IndexTTS2 必须能用「音色描述」直出。
|
||
|
||
用户口径(2026-11 第六轮):
|
||
1. 部署服务器是 Linux,没有系统 ``say`` 命令——「mac 本地(macos-say)」这条音频模型
|
||
在这台机器上永远跑不通,登记在库里只会让人选中一个不可用的模型;
|
||
2. IndexTTS2 除了参考音频克隆,还要支持**直接用描述词生成语音**:
|
||
只填「音色描述」(例:年幼小女孩、低沉老年男性)就该出对应的嗓子,
|
||
而不是必须先上传一段参考音频。
|
||
|
||
实测依据(直连 10.100.53.199:9200 提交图验证):
|
||
``easy indexTTSGenerateSimple`` 没有 emotions 输入,描述词写进去不生效;
|
||
描述词必须走 ``easy indexTTSGenerate``(全参)+ ``easy indexTTSEmotionText``
|
||
(reference_audio / voice_name / description / use_random → 输出 emotions)。
|
||
同一句台词用两组描述词实测中位基频 241.4 Hz ↔ 189.2 Hz,音色确实在变。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import importlib
|
||
|
||
from app.models import ModelSpec, PlatformVoice
|
||
from app.providers.base import VoiceGenRequest
|
||
from app.providers.comfy_assets import ComfyTTSProvider
|
||
from app.services import timbre
|
||
|
||
|
||
CFG = {"base_url": "http://127.0.0.1:9200"}
|
||
|
||
|
||
def _req(**kw) -> VoiceGenRequest:
|
||
base = dict(text="你好,我是这条声线。", label="声线A", output_path="/tmp/x.wav",
|
||
provider_voice_id="")
|
||
base.update(kw)
|
||
return VoiceGenRequest(**base)
|
||
|
||
|
||
# ------------------------------------------------------------------ 描述词图
|
||
def test_instruct_switches_graph_to_full_node_with_emotion():
|
||
"""填了音色描述 → 换全参生成节点,并挂上描述词节点(Simple 节点不接 emotions)。"""
|
||
graph = ComfyTTSProvider.graph(_req(), CFG, 1234, "nex_animation/ref.wav",
|
||
instruct="低沉老年男性")
|
||
assert graph["3"]["class_type"] == "easy indexTTSGenerate"
|
||
assert graph["5"]["class_type"] == "easy indexTTSEmotionText"
|
||
assert graph["5"]["inputs"]["description"] == "低沉老年男性"
|
||
assert graph["5"]["inputs"]["reference_audio"] == ["2", 0]
|
||
assert graph["3"]["inputs"]["emotions"] == ["5", 0]
|
||
# 全参节点的必填项一个都不能少,缺一项 ComfyUI 会在提交阶段直接拒绝整张图
|
||
for key, value in ComfyTTSProvider.FULL_DEFAULTS.items():
|
||
assert graph["3"]["inputs"][key] == value, key
|
||
assert graph["3"]["inputs"]["text"] == "你好,我是这条声线。"
|
||
assert graph["3"]["inputs"]["seed"] == 1234
|
||
|
||
|
||
def test_instruct_keeps_clone_reference_when_present():
|
||
"""有真人参考音频时克隆优先:描述词只做偏移,不该把克隆来的嗓子丢掉。"""
|
||
graph = ComfyTTSProvider.graph(_req(), CFG, 7, "nex_animation/ref.wav",
|
||
instruct="年幼小女孩")
|
||
assert graph["3"]["inputs"]["reference_audio"] == ["2", 0]
|
||
|
||
|
||
def test_description_only_mode_still_loads_the_anchor_audio():
|
||
"""只填描述词时仍要一段底声锚点:ComfyUI-Index-TTS 的 emotion 节点
|
||
``reference_audio`` 是必填项,缺了它整张图提交就被拒。
|
||
|
||
锚点用模型配置的默认参考音频,音色由描述词决定——实测同一句台词两组描述词
|
||
中位基频 241.4 Hz ↔ 189.2 Hz,锚点相同而嗓子不同。
|
||
"""
|
||
graph = ComfyTTSProvider.graph(_req(), CFG, 7, "nex_default.wav",
|
||
instruct="年幼小女孩")
|
||
assert graph["2"]["inputs"]["audio"] == "nex_default.wav"
|
||
assert graph["5"]["inputs"]["reference_audio"] == ["2", 0]
|
||
assert graph["3"]["inputs"]["reference_audio"] == ["2", 0]
|
||
assert graph["3"]["inputs"]["emotions"] == ["5", 0]
|
||
|
||
|
||
def test_plain_clone_graph_is_unchanged():
|
||
"""没填描述词时仍是原来的 zero-shot 克隆图,老行为不受影响。"""
|
||
graph = ComfyTTSProvider.graph(_req(), CFG, 7, "nex_animation/ref.wav", instruct="")
|
||
assert graph["3"]["class_type"] == "easy indexTTSGenerateSimple"
|
||
assert "emotions" not in graph["3"]["inputs"]
|
||
assert "5" not in graph
|
||
|
||
|
||
def test_capabilities_declare_voice_instruct():
|
||
caps = ComfyTTSProvider().capabilities(CFG)
|
||
assert "voice_instruct" in caps.modes
|
||
assert "voice_clone" in caps.modes
|
||
|
||
|
||
# ------------------------------------------------------------------ mac 本地下线
|
||
def test_macos_say_adapter_is_gone():
|
||
assert importlib.util.find_spec("app.providers.macos_say") is None
|
||
|
||
|
||
def test_registry_no_longer_seeds_macos_say(db):
|
||
from app.providers import registry
|
||
|
||
registry.seed_specs(db)
|
||
db.commit()
|
||
assert db.query(ModelSpec).filter(ModelSpec.provider == "macos-say").count() == 0
|
||
rows = list(db.query(ModelSpec).filter(ModelSpec.media_type == "tts").all())
|
||
assert rows, "音频模型整类不能因为下线 macos-say 而被清空"
|
||
assert "macos-say" not in {r.provider for r in rows}
|
||
indextts = [r for r in rows if r.adapter == "comfyui_tts"]
|
||
assert indextts, "IndexTTS2 必须仍在册"
|
||
assert "voice_instruct" in (indextts[0].modes or [])
|
||
|
||
|
||
def test_legacy_macos_say_row_is_retired_and_default_promoted(db):
|
||
"""库里已经登记过 macos-say(开发机残留):启动时删掉,默认值顺延给后继模型。"""
|
||
from app.providers import registry
|
||
|
||
stale = ModelSpec(media_type="tts", provider="macos-say", adapter="macos_say",
|
||
display_name="mac 本地", model="system-voice",
|
||
model_code="macos-say/system-voice", is_default=True, enabled=True)
|
||
keeper = ModelSpec(media_type="tts", provider="comfyui_tts", adapter="comfyui_tts",
|
||
display_name="IndexTTS2", model="IndexTTS-2",
|
||
model_code="comfyui/indextts2", is_default=False, enabled=True,
|
||
modes=["voice", "voice_clone", "voice_instruct"])
|
||
db.add_all([stale, keeper])
|
||
db.commit()
|
||
|
||
assert registry._retire_macos_say(db) is True
|
||
db.commit()
|
||
assert db.query(ModelSpec).filter(ModelSpec.provider == "macos-say").count() == 0
|
||
db.refresh(keeper)
|
||
assert keeper.is_default is True
|
||
# 幂等:第二次没有 macos-say 行可删,不再动默认标记
|
||
assert registry._retire_macos_say(db) is False
|
||
|
||
|
||
# ------------------------------------------------------------------ 音色解析
|
||
def test_instruct_model_is_detected_from_modes():
|
||
spec = ModelSpec(media_type="tts", provider="comfyui_tts", adapter="comfyui_tts",
|
||
display_name="IndexTTS2", model="IndexTTS-2",
|
||
modes=["voice", "voice_clone", "voice_instruct"])
|
||
assert timbre.instruct_model(spec) is True
|
||
clone_only = ModelSpec(media_type="tts", provider="comfyui_tts", adapter="comfyui_tts",
|
||
display_name="只认参考音频的模型", model="x",
|
||
modes=["voice", "voice_clone"])
|
||
assert timbre.instruct_model(clone_only) is False
|
||
|
||
|
||
def test_description_only_voice_resolves_to_instruct(db):
|
||
"""没参考音频、没性别的声线:以前只能拿模型默认参考(音色不受控),现在走描述词。"""
|
||
voice = PlatformVoice(name="描述词声线", code="instruct-only", gender="",
|
||
description="年幼小女孩,音色清亮,语速偏快",
|
||
is_active=True, is_default=False, provider_voice_id="")
|
||
db.add(voice)
|
||
db.commit()
|
||
|
||
assert timbre.instruct_text_of(voice) == "年幼小女孩,音色清亮,语速偏快"
|
||
resolved = timbre.resolve_reference(db, voice, instruct=True)
|
||
assert resolved["source"] == "instruct"
|
||
assert resolved["path"] == ""
|
||
assert "音色描述" in resolved["note"]
|
||
|
||
status = timbre.reference_status(db, voice, instruct=True)
|
||
assert status["instruct"] is True
|
||
assert status["ready"] is True
|
||
assert status["instruct_text"] == "年幼小女孩,音色清亮,语速偏快"
|
||
|
||
# 关掉描述词能力(换回只认参考音频的模型)时,预告回到原来的口径
|
||
plain = timbre.reference_status(db, voice, instruct=False)
|
||
assert plain["instruct"] is False
|
||
assert plain["source"] == "model_default"
|
||
|
||
|
||
def test_instruct_needs_a_description(db):
|
||
"""描述词是空的:不能谎称「按描述词生成」,仍按模型默认参考处理。"""
|
||
voice = PlatformVoice(name="空描述", code="instruct-empty", gender="",
|
||
description="", is_active=True, is_default=False,
|
||
provider_voice_id="")
|
||
db.add(voice)
|
||
db.commit()
|
||
assert timbre.resolve_reference(db, voice, instruct=True)["source"] == "model_default"
|
||
|
||
|
||
def test_reference_audio_still_wins_over_description(db, tmp_path):
|
||
"""参考音频优先于描述词:克隆出来的嗓子比描述词精确得多。"""
|
||
anchor = tmp_path / "anchor.wav"
|
||
anchor.write_bytes(b"RIFF" + b"\0" * 40)
|
||
voice = PlatformVoice(name="有参考", code="instruct-ref", gender="male",
|
||
description="低沉老年男性", is_active=True, is_default=False,
|
||
provider_voice_id=str(anchor))
|
||
db.add(voice)
|
||
db.commit()
|
||
|
||
resolved = timbre.resolve_reference(db, voice, instruct=True)
|
||
assert resolved["source"] == "self"
|
||
assert resolved["path"] == str(anchor)
|