mirror of
https://github.com/denizsafak/abogen.git
synced 2026-07-18 13:40:27 +02:00
refactor(webui): replace inline get_pipeline/resolve_voice_target closures with domain modules
- Replace get_pipeline() closure with PipelinePool from domain/pipeline_factory - Replace resolve_voice_target() closure with domain function from voice_utils - Remove dead _load_pipeline() function and unused is_plugin_registered import - Add 33 tests for resolve_voice_target and PipelinePool - Add 10 regression tests verifying domain extraction preserves behavior - 1131 tests pass (+61 new)
This commit is contained in:
Artem Akymenko
@@ -13,7 +13,6 @@ from typing import Any, Callable, Dict, List, Mapping, Optional
|
||||
|
||||
import numpy as np
|
||||
|
||||
from abogen.tts_plugin.utils import is_plugin_registered
|
||||
from abogen.infrastructure.exporters import ExportService
|
||||
from abogen.epub3.exporter import build_epub3_package
|
||||
from abogen.kokoro_text_normalization import ApostropheConfig, normalize_for_pipeline, HAS_NUM2WORDS
|
||||
@@ -31,10 +30,7 @@ from abogen.utils import (
|
||||
get_internal_cache_path,
|
||||
get_user_cache_path,
|
||||
get_user_output_path,
|
||||
load_config,
|
||||
)
|
||||
from abogen.tts_plugin.utils import create_pipeline
|
||||
from abogen.voice_formulas import get_new_voice
|
||||
from abogen.voice_profiles import load_profiles, normalize_profile_entry
|
||||
from abogen.llm_client import LLMClientError
|
||||
from abogen.infrastructure.subtitle_writer import create_subtitle_writer
|
||||
@@ -122,6 +118,8 @@ from abogen.domain.audio_buffer import (
|
||||
)
|
||||
from abogen.domain.audio_sink import AudioSink, open_audio_sink
|
||||
from abogen.domain.tokens import FakeToken
|
||||
from abogen.domain.pipeline_factory import PipelinePool
|
||||
from abogen.domain.voice_utils import resolve_voice_target as _resolve_voice_target
|
||||
|
||||
|
||||
from .service import Job, JobStatus
|
||||
@@ -184,8 +182,7 @@ def run_conversion_job(job: Job) -> None:
|
||||
audio_output_path: Optional[Path] = None
|
||||
extraction: Optional[Any] = None
|
||||
pipeline: Any = None
|
||||
pipelines: Dict[str, Any] = {}
|
||||
kokoro_cache_ready = False
|
||||
pipeline_pool = PipelinePool()
|
||||
normalized_profiles: Dict[str, Dict[str, Any]] = {}
|
||||
chunk_groups: Dict[int, List[Dict[str, Any]]] = {}
|
||||
active_chapter_configs: List[Dict[str, Any]] = []
|
||||
@@ -202,75 +199,23 @@ def run_conversion_job(job: Job) -> None:
|
||||
if normalized:
|
||||
normalized_profiles[str(name)] = normalized
|
||||
|
||||
def get_pipeline(provider: str) -> Any:
|
||||
nonlocal kokoro_cache_ready
|
||||
provider_norm = str(provider or "kokoro").strip().lower() or "kokoro"
|
||||
if not is_plugin_registered(provider_norm):
|
||||
provider_norm = "kokoro"
|
||||
|
||||
existing = pipelines.get(provider_norm)
|
||||
if existing is not None:
|
||||
return existing
|
||||
|
||||
if provider_norm == "supertonic":
|
||||
pipelines[provider_norm] = create_pipeline(
|
||||
"supertonic",
|
||||
)
|
||||
return pipelines[provider_norm]
|
||||
|
||||
# Kokoro
|
||||
cfg = load_config()
|
||||
disable_gpu = not job.use_gpu or not cfg.get("use_gpu", True)
|
||||
device = "cpu"
|
||||
if not disable_gpu:
|
||||
device = _select_device()
|
||||
# Create KPipeline instance directly (uses new Plugin Architecture)
|
||||
pipelines[provider_norm] = create_pipeline(
|
||||
"kokoro",
|
||||
lang_code=job.language,
|
||||
device=device
|
||||
)
|
||||
if not kokoro_cache_ready:
|
||||
_initialize_voice_cache(job)
|
||||
kokoro_cache_ready = True
|
||||
return pipelines[provider_norm]
|
||||
|
||||
def resolve_voice_target(raw_spec: str) -> tuple[str, str, Optional[float], Optional[int]]:
|
||||
"""Return (provider, voice_spec, speed_override, steps_override)."""
|
||||
spec = str(raw_spec or "").strip()
|
||||
speaker_name, _ = _split_speaker_reference(spec)
|
||||
if speaker_name and speaker_name in normalized_profiles:
|
||||
entry = normalized_profiles[speaker_name]
|
||||
provider = str(entry.get("provider") or "kokoro").strip().lower() or "kokoro"
|
||||
if provider == "supertonic":
|
||||
voice = str(entry.get("voice") or getattr(job, "voice", "M1") or "M1").strip() or "M1"
|
||||
steps = int(entry.get("total_steps") or getattr(job, "supertonic_total_steps", 5) or 5)
|
||||
speed = float(entry.get("speed") or getattr(job, "speed", 1.0) or 1.0)
|
||||
return "supertonic", _supertonic_voice_from_spec(voice, getattr(job, "voice", "M1")), speed, steps
|
||||
formula = _formula_from_kokoro_entry(entry)
|
||||
return "kokoro", formula or spec, None, None
|
||||
|
||||
fallback_provider = str(getattr(job, "tts_provider", "kokoro") or "kokoro").strip().lower() or "kokoro"
|
||||
inferred = _infer_provider_from_spec(spec, fallback=fallback_provider)
|
||||
if inferred == "supertonic":
|
||||
return "supertonic", _supertonic_voice_from_spec(spec, getattr(job, "voice", "M1")), None, None
|
||||
return "kokoro", spec, None, None
|
||||
|
||||
def resolve_voice_choice(raw_spec: str) -> tuple[str, str, Any, Optional[float], Optional[int]]:
|
||||
"""Resolve a raw voice spec into (provider, resolved_spec, choice, speed, steps).
|
||||
|
||||
For Kokoro formulas, `choice` will be a resolved voice tensor (via `voice_formulas`).
|
||||
For SuperTonic, `choice` will be a valid SuperTonic voice id.
|
||||
"""
|
||||
|
||||
provider, resolved, speed, steps = resolve_voice_target(raw_spec)
|
||||
"""Resolve a raw voice spec into (provider, resolved_spec, choice, speed, steps)."""
|
||||
provider, resolved, speed, steps = _resolve_voice_target(
|
||||
raw_spec,
|
||||
normalized_profiles,
|
||||
job_voice=getattr(job, "voice", "M1"),
|
||||
job_tts_provider=getattr(job, "tts_provider", "kokoro"),
|
||||
job_supertonic_total_steps=getattr(job, "supertonic_total_steps", 5),
|
||||
job_speed=getattr(job, "speed", 1.0),
|
||||
)
|
||||
cache_key = f"{provider}:{resolved}" if resolved else provider
|
||||
cached = voice_cache.get(cache_key)
|
||||
if cached is not None:
|
||||
return provider, resolved, cached, speed, steps
|
||||
|
||||
if provider == "kokoro":
|
||||
kokoro_backend = get_pipeline("kokoro")
|
||||
kokoro_backend = pipeline_pool.get("kokoro", job.language, job.use_gpu, job=job)
|
||||
choice = _resolve_voice(kokoro_backend, resolved, job.use_gpu)
|
||||
else:
|
||||
choice = resolved
|
||||
@@ -405,9 +350,13 @@ def run_conversion_job(job: Job) -> None:
|
||||
|
||||
base_voice_spec = _job_voice_fallback(job)
|
||||
voice_cache: Dict[str, Any] = {}
|
||||
base_provider, base_voice_resolved, _, _ = resolve_voice_target(base_voice_spec)
|
||||
base_provider, base_voice_resolved, _, _ = _resolve_voice_target(
|
||||
base_voice_spec, normalized_profiles,
|
||||
job_voice=getattr(job, "voice", "M1"),
|
||||
job_tts_provider=getattr(job, "tts_provider", "kokoro"),
|
||||
)
|
||||
if base_provider == "kokoro" and base_voice_resolved and "*" not in base_voice_resolved:
|
||||
kokoro_backend = get_pipeline("kokoro")
|
||||
kokoro_backend = pipeline_pool.get("kokoro", job.language, job.use_gpu, job=job)
|
||||
voice_cache[f"kokoro:{base_voice_resolved}"] = _resolve_voice(kokoro_backend, base_voice_resolved, job.use_gpu)
|
||||
processed_chars = 0
|
||||
current_time = 0.0
|
||||
@@ -473,7 +422,7 @@ def run_conversion_job(job: Job) -> None:
|
||||
|
||||
provider = str(tts_provider or getattr(job, "tts_provider", "kokoro") or "kokoro").strip().lower() or "kokoro"
|
||||
if provider == "supertonic":
|
||||
supertonic_pipeline = get_pipeline("supertonic")
|
||||
supertonic_pipeline = pipeline_pool.get("supertonic", job.language, job.use_gpu, job=job)
|
||||
voice_name = _supertonic_voice_from_spec(voice_choice, getattr(job, "voice", "M1"))
|
||||
segment_iter = supertonic_pipeline(
|
||||
normalized,
|
||||
@@ -483,7 +432,7 @@ def run_conversion_job(job: Job) -> None:
|
||||
total_steps=int(supertonic_steps_override if supertonic_steps_override is not None else getattr(job, "supertonic_total_steps", 5)),
|
||||
)
|
||||
else:
|
||||
kokoro_backend = get_pipeline("kokoro")
|
||||
kokoro_backend = pipeline_pool.get("kokoro", job.language, job.use_gpu, job=job)
|
||||
segment_iter = kokoro_backend(
|
||||
normalized,
|
||||
voice=voice_choice,
|
||||
@@ -605,12 +554,18 @@ def run_conversion_job(job: Job) -> None:
|
||||
if not chapter_voice_spec:
|
||||
chapter_voice_spec = base_voice_spec
|
||||
|
||||
chapter_provider, chapter_voice_resolved, chapter_speed, chapter_steps = resolve_voice_target(chapter_voice_spec)
|
||||
chapter_provider, chapter_voice_resolved, chapter_speed, chapter_steps = _resolve_voice_target(
|
||||
chapter_voice_spec, normalized_profiles,
|
||||
job_voice=getattr(job, "voice", "M1"),
|
||||
job_tts_provider=getattr(job, "tts_provider", "kokoro"),
|
||||
job_supertonic_total_steps=getattr(job, "supertonic_total_steps", 5),
|
||||
job_speed=getattr(job, "speed", 1.0),
|
||||
)
|
||||
chapter_cache_key = f"{chapter_provider}:{chapter_voice_resolved}" if chapter_voice_resolved else chapter_provider
|
||||
if chapter_provider == "kokoro":
|
||||
voice_choice = voice_cache.get(chapter_cache_key)
|
||||
if voice_choice is None:
|
||||
kokoro_backend = get_pipeline("kokoro")
|
||||
kokoro_backend = pipeline_pool.get("kokoro", job.language, job.use_gpu, job=job)
|
||||
voice_choice = _resolve_voice(kokoro_backend, chapter_voice_resolved, job.use_gpu)
|
||||
voice_cache[chapter_cache_key] = voice_choice
|
||||
else:
|
||||
@@ -743,12 +698,18 @@ def run_conversion_job(job: Job) -> None:
|
||||
chunk_steps_use = chapter_steps
|
||||
chunk_voice_choice = voice_choice
|
||||
else:
|
||||
chunk_provider, chunk_voice_resolved, chunk_speed_use, chunk_steps_use = resolve_voice_target(chunk_voice_spec)
|
||||
chunk_provider, chunk_voice_resolved, chunk_speed_use, chunk_steps_use = _resolve_voice_target(
|
||||
chunk_voice_spec, normalized_profiles,
|
||||
job_voice=getattr(job, "voice", "M1"),
|
||||
job_tts_provider=getattr(job, "tts_provider", "kokoro"),
|
||||
job_supertonic_total_steps=getattr(job, "supertonic_total_steps", 5),
|
||||
job_speed=getattr(job, "speed", 1.0),
|
||||
)
|
||||
chunk_cache_key = f"{chunk_provider}:{chunk_voice_resolved}" if chunk_voice_resolved else chunk_provider
|
||||
if chunk_provider == "kokoro":
|
||||
chunk_voice_choice = voice_cache.get(chunk_cache_key)
|
||||
if chunk_voice_choice is None:
|
||||
kokoro_backend = get_pipeline("kokoro")
|
||||
kokoro_backend = pipeline_pool.get("kokoro", job.language, job.use_gpu, job=job)
|
||||
chunk_voice_choice = _resolve_voice(
|
||||
kokoro_backend,
|
||||
chunk_voice_resolved,
|
||||
@@ -1054,12 +1015,7 @@ def run_conversion_job(job: Job) -> None:
|
||||
|
||||
# Explicitly release the pipeline and force garbage collection to prevent
|
||||
# memory accumulation in the worker process, which can lead to host lockups.
|
||||
for p in pipelines.values():
|
||||
try:
|
||||
p.dispose()
|
||||
except Exception:
|
||||
pass
|
||||
pipelines.clear()
|
||||
pipeline_pool.dispose_all()
|
||||
pipeline = None
|
||||
gc.collect()
|
||||
try:
|
||||
@@ -1100,21 +1056,6 @@ def run_conversion_job(job: Job) -> None:
|
||||
) from exc
|
||||
|
||||
|
||||
def _load_pipeline(job: Job):
|
||||
cfg = load_config()
|
||||
disable_gpu = not job.use_gpu or not cfg.get("use_gpu", True)
|
||||
provider = str(getattr(job, "tts_provider", "kokoro") or "kokoro").strip().lower()
|
||||
if provider == "supertonic":
|
||||
return create_pipeline(
|
||||
"supertonic",
|
||||
)
|
||||
|
||||
device = "cpu"
|
||||
if not disable_gpu:
|
||||
device = _select_device()
|
||||
return create_pipeline("kokoro", lang_code=job.language, device=device)
|
||||
|
||||
|
||||
def _prepare_output_dir(job: Job) -> Path:
|
||||
from platformdirs import user_desktop_dir # type: ignore[import-not-found]
|
||||
|
||||
|
||||
@@ -0,0 +1,175 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from abogen.domain.pipeline_factory import (
|
||||
PipelinePool,
|
||||
create_pipeline_for_job,
|
||||
dispose_pipelines,
|
||||
resolve_device,
|
||||
)
|
||||
|
||||
|
||||
class TestResolveDevice:
|
||||
@patch("abogen.utils.load_config", return_value={"use_gpu": True})
|
||||
@patch("abogen.domain.pipeline_factory.select_device", return_value="cuda:0")
|
||||
def test_gpu_enabled(self, _sel, _cfg):
|
||||
assert resolve_device(use_gpu=True) == "cuda:0"
|
||||
|
||||
@patch("abogen.utils.load_config", return_value={"use_gpu": True})
|
||||
def test_gpu_disabled_by_job(self, _cfg):
|
||||
assert resolve_device(use_gpu=False) == "cpu"
|
||||
|
||||
@patch("abogen.utils.load_config", return_value={"use_gpu": False})
|
||||
@patch("abogen.domain.pipeline_factory.select_device", return_value="cuda:0")
|
||||
def test_gpu_disabled_by_config(self, _sel, _cfg):
|
||||
assert resolve_device(use_gpu=True) == "cpu"
|
||||
|
||||
|
||||
class TestCreatePipelineForJob:
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=True)
|
||||
def test_supertonic_provider(self, _reg, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
result = create_pipeline_for_job("supertonic", "en", use_gpu=True)
|
||||
mock_create.assert_called_once_with("supertonic")
|
||||
assert result is mock_create.return_value
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=True)
|
||||
@patch("abogen.domain.pipeline_factory.resolve_device", return_value="cpu")
|
||||
def test_kokoro_provider(self, _dev, _reg, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
result = create_pipeline_for_job("kokoro", "en", use_gpu=False)
|
||||
mock_create.assert_called_once_with("kokoro", lang_code="en", device="cpu")
|
||||
assert result is mock_create.return_value
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=False)
|
||||
@patch("abogen.domain.pipeline_factory.resolve_device", return_value="cpu")
|
||||
def test_unknown_provider_falls_back_to_kokoro(self, _dev, _reg, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
result = create_pipeline_for_job("unknown_provider", "en", use_gpu=False)
|
||||
mock_create.assert_called_once_with("kokoro", lang_code="en", device="cpu")
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=True)
|
||||
@patch("abogen.domain.pipeline_factory.resolve_device", return_value="cpu")
|
||||
def test_empty_provider_defaults_to_kokoro(self, _dev, _reg, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
result = create_pipeline_for_job("", "en", use_gpu=False)
|
||||
mock_create.assert_called_once_with("kokoro", lang_code="en", device="cpu")
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=True)
|
||||
@patch("abogen.domain.pipeline_factory.resolve_device", return_value="cpu")
|
||||
def test_none_provider_defaults_to_kokoro(self, _dev, _reg, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
result = create_pipeline_for_job(None, "en", use_gpu=False)
|
||||
mock_create.assert_called_once_with("kokoro", lang_code="en", device="cpu")
|
||||
|
||||
|
||||
class TestDisposePipelines:
|
||||
def test_disposes_all_and_clears(self):
|
||||
p1 = MagicMock()
|
||||
p2 = MagicMock()
|
||||
pipelines = {"kokoro": p1, "supertonic": p2}
|
||||
dispose_pipelines(pipelines)
|
||||
p1.dispose.assert_called_once()
|
||||
p2.dispose.assert_called_once()
|
||||
assert pipelines == {}
|
||||
|
||||
def test_handles_dispose_error(self):
|
||||
p1 = MagicMock()
|
||||
p1.dispose.side_effect = RuntimeError("boom")
|
||||
pipelines = {"kokoro": p1}
|
||||
dispose_pipelines(pipelines)
|
||||
assert pipelines == {}
|
||||
|
||||
def test_empty_dict(self):
|
||||
pipelines = {}
|
||||
dispose_pipelines(pipelines)
|
||||
assert pipelines == {}
|
||||
|
||||
|
||||
class TestPipelinePool:
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_get_creates_and_caches(self, _cache, mock_create):
|
||||
mock_pipeline = MagicMock()
|
||||
mock_create.return_value = mock_pipeline
|
||||
pool = PipelinePool()
|
||||
|
||||
result = pool.get("kokoro", "en", use_gpu=True)
|
||||
assert result is mock_pipeline
|
||||
mock_create.assert_called_once()
|
||||
|
||||
result2 = pool.get("kokoro", "en", use_gpu=True)
|
||||
assert result2 is mock_pipeline
|
||||
assert mock_create.call_count == 1
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_get_initializes_voice_cache_once(self, mock_cache, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
pool = PipelinePool()
|
||||
|
||||
job = MagicMock()
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
assert mock_cache.call_count == 1
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
assert mock_cache.call_count == 1
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
def test_get_no_job_skips_voice_cache(self, mock_create, mock_cache):
|
||||
mock_create.return_value = MagicMock()
|
||||
pool = PipelinePool()
|
||||
pool.get("kokoro", "en", use_gpu=True)
|
||||
mock_cache.assert_not_called()
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
def test_get_separately_per_provider(self, mock_create):
|
||||
p1 = MagicMock(name="kokoro")
|
||||
p2 = MagicMock(name="supertonic")
|
||||
mock_create.side_effect = [p1, p2]
|
||||
pool = PipelinePool()
|
||||
|
||||
r1 = pool.get("kokoro", "en", use_gpu=True)
|
||||
r2 = pool.get("supertonic", "en", use_gpu=True)
|
||||
assert r1 is p1
|
||||
assert r2 is p2
|
||||
assert mock_create.call_count == 2
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_dispose_all(self, mock_cache, mock_create):
|
||||
p1 = MagicMock(name="kokoro")
|
||||
p2 = MagicMock(name="supertonic")
|
||||
mock_create.side_effect = [p1, p2]
|
||||
pool = PipelinePool()
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True)
|
||||
pool.get("supertonic", "en", use_gpu=True)
|
||||
pool.dispose_all()
|
||||
|
||||
p1.dispose.assert_called_once()
|
||||
p2.dispose.assert_called_once()
|
||||
assert pool._pipelines == {}
|
||||
assert pool._voice_cache_initialized is False
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
def test_dispose_empty_pool(self, mock_create):
|
||||
pool = PipelinePool()
|
||||
pool.dispose_all()
|
||||
mock_create.assert_not_called()
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
@patch("abogen.domain.pipeline_factory.is_plugin_registered", return_value=False)
|
||||
def test_unknown_provider_falls_back(self, _reg, _cache, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
pool = PipelinePool()
|
||||
pool.get("bogus_provider", "en", use_gpu=True)
|
||||
mock_create.assert_called_once_with("kokoro", "en", True)
|
||||
@@ -0,0 +1,195 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from unittest.mock import patch
|
||||
|
||||
from abogen.domain.voice_utils import (
|
||||
coerce_truthy,
|
||||
formula_from_kokoro_entry,
|
||||
infer_provider_from_spec,
|
||||
resolve_voice_target,
|
||||
split_speaker_reference,
|
||||
supertonic_voice_from_spec,
|
||||
)
|
||||
|
||||
|
||||
class TestSplitSpeakerReference:
|
||||
def test_speaker_prefix(self):
|
||||
assert split_speaker_reference("speaker:af_sarah") == ("af_sarah", "speaker:af_sarah")
|
||||
|
||||
def test_profile_prefix(self):
|
||||
assert split_speaker_reference("profile:custom") == ("custom", "profile:custom")
|
||||
|
||||
def test_no_prefix(self):
|
||||
assert split_speaker_reference("af_sarah") == (None, "af_sarah")
|
||||
|
||||
def test_empty(self):
|
||||
assert split_speaker_reference("") == (None, "")
|
||||
|
||||
def test_none(self):
|
||||
assert split_speaker_reference(None) == (None, "")
|
||||
|
||||
def test_unknown_prefix(self):
|
||||
assert split_speaker_reference("unknown:name") == (None, "unknown:name")
|
||||
|
||||
def test_empty_name_after_colon(self):
|
||||
assert split_speaker_reference("speaker:") == (None, "speaker:")
|
||||
|
||||
|
||||
class TestSupertonicVoiceFromSpec:
|
||||
def test_uppercase_passthrough(self):
|
||||
assert supertonic_voice_from_spec("M1", "M1") == "M1"
|
||||
|
||||
def test_lowercase_converted(self):
|
||||
assert supertonic_voice_from_spec("m1", "M1") == "M1"
|
||||
|
||||
def test_empty_spec_uses_fallback(self):
|
||||
assert supertonic_voice_from_spec("", "F1") == "F1"
|
||||
|
||||
def test_formula_spec_uses_fallback(self):
|
||||
assert supertonic_voice_from_spec("af_sarah*0.5+bf_emma*0.5", "M1") == "M1"
|
||||
|
||||
def test_empty_both_gives_default(self):
|
||||
assert supertonic_voice_from_spec("", "") == "M1"
|
||||
|
||||
|
||||
class TestFormulaFromKokoroEntry:
|
||||
def test_single_voice(self):
|
||||
entry = {"voices": [["af_sarah", 1.0]]}
|
||||
result = formula_from_kokoro_entry(entry)
|
||||
assert "af_sarah" in result
|
||||
assert "1.000000" in result
|
||||
|
||||
def test_weighted_mix(self):
|
||||
entry = {"voices": [["af_sarah", 0.6], ["bf_emma", 0.4]]}
|
||||
result = formula_from_kokoro_entry(entry)
|
||||
assert "af_sarah" in result
|
||||
assert "bf_emma" in result
|
||||
assert "+" in result
|
||||
|
||||
def test_empty_voices(self):
|
||||
assert formula_from_kokoro_entry({"voices": []}) == ""
|
||||
|
||||
def test_missing_voices_key(self):
|
||||
assert formula_from_kokoro_entry({}) == ""
|
||||
|
||||
def test_invalid_entries_filtered(self):
|
||||
entry = {"voices": [["af_sarah", "bad"], ["bf_emma", 0.5]]}
|
||||
result = formula_from_kokoro_entry(entry)
|
||||
assert "bf_emma" in result
|
||||
assert "af_sarah" not in result
|
||||
|
||||
|
||||
class TestCoerceTruthy:
|
||||
def test_bool_passthrough(self):
|
||||
assert coerce_truthy(True) is True
|
||||
assert coerce_truthy(False) is False
|
||||
|
||||
def test_string_true(self):
|
||||
assert coerce_truthy("yes") is True
|
||||
assert coerce_truthy("1") is True
|
||||
|
||||
def test_string_false(self):
|
||||
assert coerce_truthy("false") is False
|
||||
assert coerce_truthy("0") is False
|
||||
assert coerce_truthy("") is False
|
||||
|
||||
def test_none_default(self):
|
||||
assert coerce_truthy(None) is True
|
||||
assert coerce_truthy(None, False) is False
|
||||
|
||||
def test_int(self):
|
||||
assert coerce_truthy(1) is True
|
||||
assert coerce_truthy(0) is False
|
||||
|
||||
|
||||
class TestInferProviderFromSpec:
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah", "bf_emma"])
|
||||
def test_known_kokoro_voice(self, _mock):
|
||||
assert infer_provider_from_spec("af_sarah") == "kokoro"
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_uppercase_supertonic(self, _mock):
|
||||
assert infer_provider_from_spec("M1") == "supertonic"
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_formula_kokoro(self, _mock):
|
||||
assert infer_provider_from_spec("af_sarah*0.5+bf_emma*0.5") == "kokoro"
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_empty_fallback(self, _mock):
|
||||
assert infer_provider_from_spec("", "kokoro") == "kokoro"
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_unknown_falls_back(self, _mock):
|
||||
assert infer_provider_from_spec("unknown_xyz", "supertonic") == "supertonic"
|
||||
|
||||
|
||||
class TestResolveVoiceTarget:
|
||||
def test_empty_spec_kokoro_default(self):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"", {}, job_voice="af_sarah", job_tts_provider="kokoro",
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert spec == ""
|
||||
|
||||
def test_speaker_profile_kokoro(self):
|
||||
profiles = {
|
||||
"narrator": {
|
||||
"provider": "kokoro",
|
||||
"voices": [["af_sarah", 0.7], ["bf_emma", 0.3]],
|
||||
},
|
||||
}
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"speaker:narrator", profiles,
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert "af_sarah" in spec
|
||||
assert speed is None
|
||||
assert steps is None
|
||||
|
||||
def test_speaker_profile_supertonic(self):
|
||||
profiles = {
|
||||
"narrator": {
|
||||
"provider": "supertonic",
|
||||
"voice": "F1",
|
||||
"speed": 1.2,
|
||||
"total_steps": 10,
|
||||
},
|
||||
}
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"speaker:narrator", profiles,
|
||||
job_voice="M1", job_speed=1.0, job_supertonic_total_steps=5,
|
||||
)
|
||||
assert provider == "supertonic"
|
||||
assert spec == "F1"
|
||||
assert speed == 1.2
|
||||
assert steps == 10
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_direct_supertonic_spec(self, _mock):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"M1", {},
|
||||
job_voice="M1",
|
||||
)
|
||||
assert provider == "supertonic"
|
||||
assert spec == "M1"
|
||||
|
||||
@patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"])
|
||||
def test_direct_kokoro_spec(self, _mock):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"af_sarah", {},
|
||||
job_tts_provider="kokoro",
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert spec == "af_sarah"
|
||||
|
||||
def test_profile_missing_provider_defaults_kokoro(self):
|
||||
profiles = {
|
||||
"narrator": {
|
||||
"voices": [["af_sarah", 1.0]],
|
||||
},
|
||||
}
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"speaker:narrator", profiles,
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
@@ -0,0 +1,145 @@
|
||||
"""Regression tests: domain extraction must not break webui conversion_runner.
|
||||
|
||||
These tests verify that the refactored WebUI code paths still call into the
|
||||
correct domain functions and produce the same results as the old inline logic.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from abogen.domain.voice_utils import resolve_voice_target
|
||||
from abogen.domain.pipeline_factory import PipelinePool
|
||||
|
||||
|
||||
class TestResolveVoiceTargetRegression:
|
||||
"""Verify that the domain resolve_voice_target produces the same results
|
||||
as the old closure in conversion_runner.py."""
|
||||
|
||||
def test_empty_spec_returns_kokoro_default(self):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"", {}, job_voice="af_sarah", job_tts_provider="kokoro",
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert spec == ""
|
||||
|
||||
def test_speaker_in_profile_kokoro(self):
|
||||
profiles = {
|
||||
"narrator": {
|
||||
"provider": "kokoro",
|
||||
"voices": [["af_sarah", 0.7], ["bf_emma", 0.3]],
|
||||
},
|
||||
}
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"speaker:narrator", profiles,
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert "af_sarah" in spec
|
||||
assert speed is None
|
||||
assert steps is None
|
||||
|
||||
def test_speaker_in_profile_supertonic(self):
|
||||
profiles = {
|
||||
"narrator": {
|
||||
"provider": "supertonic",
|
||||
"voice": "F1",
|
||||
"speed": 1.2,
|
||||
"total_steps": 10,
|
||||
},
|
||||
}
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"speaker:narrator", profiles,
|
||||
job_voice="M1", job_speed=1.0, job_supertonic_total_steps=5,
|
||||
)
|
||||
assert provider == "supertonic"
|
||||
assert spec == "F1"
|
||||
assert speed == 1.2
|
||||
assert steps == 10
|
||||
|
||||
def test_unknown_speaker_infers_from_spec(self):
|
||||
with patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"]):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"af_sarah", {}, job_tts_provider="kokoro",
|
||||
)
|
||||
assert provider == "kokoro"
|
||||
assert spec == "af_sarah"
|
||||
|
||||
def test_uppercase_spec_infers_supertonic(self):
|
||||
with patch("abogen.domain.voice_utils.get_voices", return_value=["af_sarah"]):
|
||||
provider, spec, speed, steps = resolve_voice_target(
|
||||
"M1", {}, job_voice="M1",
|
||||
)
|
||||
assert provider == "supertonic"
|
||||
assert spec == "M1"
|
||||
|
||||
|
||||
class TestPipelinePoolRegression:
|
||||
"""Verify that PipelinePool behaves like the old inline get_pipeline closure."""
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_same_provider_returns_cached_pipeline(self, _cache, mock_create):
|
||||
mock_pipeline = MagicMock()
|
||||
mock_create.return_value = mock_pipeline
|
||||
pool = PipelinePool()
|
||||
|
||||
r1 = pool.get("kokoro", "en", use_gpu=True)
|
||||
r2 = pool.get("kokoro", "en", use_gpu=True)
|
||||
assert r1 is r2
|
||||
assert mock_create.call_count == 1
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_different_providers_get_separate_pipelines(self, _cache, mock_create):
|
||||
p1 = MagicMock(name="kokoro")
|
||||
p2 = MagicMock(name="supertonic")
|
||||
mock_create.side_effect = [p1, p2]
|
||||
pool = PipelinePool()
|
||||
|
||||
r1 = pool.get("kokoro", "en", use_gpu=True)
|
||||
r2 = pool.get("supertonic", "en", use_gpu=True)
|
||||
assert r1 is p1
|
||||
assert r2 is p2
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_dispose_all_cleans_up(self, _cache, mock_create):
|
||||
p1 = MagicMock()
|
||||
p2 = MagicMock()
|
||||
mock_create.side_effect = [p1, p2]
|
||||
pool = PipelinePool()
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True)
|
||||
pool.get("supertonic", "en", use_gpu=True)
|
||||
pool.dispose_all()
|
||||
|
||||
p1.dispose.assert_called_once()
|
||||
p2.dispose.assert_called_once()
|
||||
assert pool._pipelines == {}
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_voice_cache_initialized_only_once(self, mock_cache, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
pool = PipelinePool()
|
||||
job = MagicMock()
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
assert mock_cache.call_count == 1
|
||||
|
||||
@patch("abogen.domain.pipeline_factory.create_pipeline_for_job")
|
||||
@patch("abogen.domain.pipeline_factory.initialize_voice_cache")
|
||||
def test_after_dispose_voice_cache_can_reinitialize(self, mock_cache, mock_create):
|
||||
mock_create.return_value = MagicMock()
|
||||
pool = PipelinePool()
|
||||
job = MagicMock()
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
assert mock_cache.call_count == 1
|
||||
|
||||
pool.dispose_all()
|
||||
assert pool._voice_cache_initialized is False
|
||||
|
||||
pool.get("kokoro", "en", use_gpu=True, job=job)
|
||||
assert mock_cache.call_count == 2
|
||||
Reference in New Issue
Block a user