diff --git a/backend/Dockerfile.gpu-base b/backend/Dockerfile.gpu-base index 0f4cfc24..6eeccf3f 100644 --- a/backend/Dockerfile.gpu-base +++ b/backend/Dockerfile.gpu-base @@ -104,12 +104,12 @@ RUN --mount=type=cache,target=/root/.cache/pip \ # Installing torch first means audio-separator[gpu] sees it as already satisfied. # # PINNED to an exact version: an unpinned install silently picked up 0.47.0 on the -# 2026-10-17 rebuild, and on L4 its mel-band RoFormer karaoke models run 3-5x slower -# than 0.44.2 (gabox_v2 ~26s -> 149s, becruily ~27s -> 157s for a ~3-min track; -# YAML overlap/batch are unchanged, so it is in the 0.45-0.47 inference changes). -# Total separation went from ~5 to ~10-16 min and the daily E2E started failing. -# Only bump this after timing a real job on the new version (see BACKLOG). -ARG AUDIO_SEPARATOR_VERSION=0.44.2 +# 2026-10-17 rebuild and separation went from ~5 to ~10-16 min. Cause: 0.47 (#299) made +# RoFormer `overlap` a window count defaulting to each model YAML's num_overlap (4-8 for +# the karaoke models = 4-6x the forward passes of 0.44's fixed 8 s step). karaoke_gen's +# audio_processor now passes overlap=2 on >= 0.47 (SEPARATOR_MDXC_PARAMS). Time a real +# job before bumping this, and read the audio-separator release notes for compute changes. +ARG AUDIO_SEPARATOR_VERSION=0.47.1 RUN --mount=type=cache,target=/root/.cache/pip \ pip install torch==2.6.0+cu126 torchvision==0.21.0+cu126 --index-url https://download.pytorch.org/whl/cu126 && \ pip install "audio-separator[gpu]==${AUDIO_SEPARATOR_VERSION}" diff --git a/karaoke_gen/audio_processor.py b/karaoke_gen/audio_processor.py index 4626b204..ccc5d53e 100644 --- a/karaoke_gen/audio_processor.py +++ b/karaoke_gen/audio_processor.py @@ -22,6 +22,33 @@ from datetime import datetime _UNSET = object() +# audio-separator >= 0.47 defaults RoFormer `overlap` to each model YAML's num_overlap, +# counted in windows. The karaoke models set 4-8, which is 4-6x the forward passes we ran +# on 0.44 (gabox_v2 ~26s -> 149s per track on an L4). Two windows keeps chunk seams smooth +# at ~1.5x the 0.44 cost; the instrumental models' YAMLs already use 2. +# Before 0.47 `overlap` meant a step in seconds (2 = 4x slower), so only pass it on >= 0.47. +SEPARATOR_MDXC_PARAMS = { + "segment_size": 256, + "override_model_segment_size": False, + "batch_size": None, + "overlap": 2, + "pitch_shift": 0, +} +WINDOW_OVERLAP_MIN_VERSION = (0, 47) + + +def _separator_kwargs(): + """Extra Separator kwargs for the installed audio-separator version.""" + try: + from importlib.metadata import version + + installed = tuple(int(part) for part in version("audio-separator").split(".")[:2]) + except Exception: + return {} + if installed < WINDOW_OVERLAP_MIN_VERSION: + return {} + return {"mdxc_params": dict(SEPARATOR_MDXC_PARAMS)} + def _import_remote_client_cls(): try: @@ -183,6 +210,7 @@ class AudioProcessor: log_formatter=self.log_formatter, model_file_dir=self.model_file_dir, output_format=self.lossless_output_format, + **_separator_kwargs(), ) separator.load_model(model_filename=model_name) @@ -357,6 +385,7 @@ class AudioProcessor: log_formatter=self.log_formatter, model_file_dir=self.model_file_dir, output_format=self.lossless_output_format, + **_separator_kwargs(), output_dir=stems_dir, ensemble_preset=instrumental_preset, ) @@ -395,6 +424,7 @@ class AudioProcessor: log_formatter=self.log_formatter, model_file_dir=self.model_file_dir, output_format=self.lossless_output_format, + **_separator_kwargs(), ) result["clean_instrumental"] = self._separate_clean_instrumental( separator, audio_file, artist_title, track_output_dir, stems_dir @@ -425,6 +455,7 @@ class AudioProcessor: log_formatter=self.log_formatter, model_file_dir=self.model_file_dir, output_format=self.lossless_output_format, + **_separator_kwargs(), output_dir=stems_dir, ensemble_preset=karaoke_preset, ) diff --git a/pyproject.toml b/pyproject.toml index 176716e5..f4b3b0c4 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "karaoke-gen" -version = "0.278.15" +version = "0.278.16" description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens." authors = ["Andrew Beveridge "] license = "MIT" diff --git a/tests/unit/test_audio_processor_local_gpu.py b/tests/unit/test_audio_processor_local_gpu.py index 044e771b..cab78191 100644 --- a/tests/unit/test_audio_processor_local_gpu.py +++ b/tests/unit/test_audio_processor_local_gpu.py @@ -267,6 +267,40 @@ class TestLocalSeparationWithPresets: stage2_kwargs = mock_separator_cls.call_args_list[1][1] assert stage2_kwargs.get("ensemble_preset") == "karaoke" + @patch.dict(os.environ, {}, clear=False) + @patch("importlib.metadata.version", return_value="0.47.1") + @patch("karaoke_gen.audio_processor.shutil") + @patch("karaoke_gen.audio_processor.Separator") + def test_both_stages_pass_overlap_two_on_window_overlap_separator(self, mock_separator_cls, mock_shutil, _mock_version): + """Stage 1 and the karaoke ensemble (num_overlap 4-8 in YAML) both run with overlap=2.""" + os.environ.pop("AUDIO_SEPARATOR_API_URL", None) + + stems_dir = "/tmp/stems" + mock_sep1 = MagicMock() + mock_sep1.separate.return_value = [ + f"{stems_dir}/Song_(Vocals)_preset_instrumental_clean.flac", + f"{stems_dir}/Song_(Instrumental)_preset_instrumental_clean.flac", + ] + mock_sep2 = MagicMock() + mock_sep2.separate.return_value = [ + f"{stems_dir}/Artist - Title (Vocals)_(Vocals)_preset_karaoke.flac", + f"{stems_dir}/Artist - Title (Vocals)_(No Vocal)_preset_karaoke.flac", + ] + mock_separator_cls.side_effect = [mock_sep1, mock_sep2] + mock_shutil.move.side_effect = lambda src, dst: dst + mock_shutil.copy2 = MagicMock() + + with patch.object(self.processor, '_create_stems_directory', return_value=stems_dir): + with patch.object(self.processor, '_normalize_audio_files'): + with patch.object(self.processor, '_generate_combined_instrumentals', return_value={}): + self.processor.process_audio_separation( + "/tmp/test.wav", "Artist - Title", "/tmp/output" + ) + + assert mock_separator_cls.call_count == 2 + for call in mock_separator_cls.call_args_list: + assert call[1]["mdxc_params"]["overlap"] == 2 + class TestEnsembleStemTagParsing: """Tests for stem tag extraction from ensemble preset output filenames. @@ -465,3 +499,35 @@ class TestEnsembleStemTagParsing: # Should not have classified anything assert result["clean_instrumental"].get("vocals") is None assert result["clean_instrumental"].get("instrumental") is None + + +class TestSeparatorOverlapParams: + """audio-separator >= 0.47 counts RoFormer overlap in windows; gen pins 2 to keep karaoke models fast.""" + + def _kwargs_for_version(self, installed): + from karaoke_gen import audio_processor + + with patch("importlib.metadata.version", return_value=installed): + return audio_processor._separator_kwargs() + + def test_window_overlap_versions_get_overlap_two(self): + for installed in ("0.47.0", "0.47.1", "0.48.2", "1.0.0"): + kwargs = self._kwargs_for_version(installed) + assert kwargs["mdxc_params"]["overlap"] == 2, installed + assert kwargs["mdxc_params"]["batch_size"] is None + + def test_seconds_overlap_versions_keep_library_defaults(self): + # Before 0.47 overlap=2 meant a 2 s step: 4x the passes of the 8 s default. + for installed in ("0.44.1", "0.44.2", "0.46.0"): + assert self._kwargs_for_version(installed) == {}, installed + + def test_unknown_version_keeps_library_defaults(self): + from karaoke_gen import audio_processor + + with patch("importlib.metadata.version", side_effect=Exception("not installed")): + assert audio_processor._separator_kwargs() == {} + + def test_returns_a_fresh_copy(self): + kwargs = self._kwargs_for_version("0.47.1") + kwargs["mdxc_params"]["overlap"] = 8 + assert self._kwargs_for_version("0.47.1")["mdxc_params"]["overlap"] == 2