formatting (1babf7f9) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

ivas_processing_scripts/init.py

+8 −2

Original line number	Diff line number	Diff line
		@@ -36,6 +36,7 @@ from itertools import repeat
		import yaml

		from ivas_processing_scripts.audiotools.metadata import check_ISM_metadata
		from ivas_processing_scripts.audiotools.wrappers.bs1770 import scale_files
		from ivas_processing_scripts.constants import (
		LOGGER_DATEFMT,
		LOGGER_FORMAT,
		@@ -49,7 +50,6 @@ from ivas_processing_scripts.processing.processing import (
		process_item,
		)
		from ivas_processing_scripts.utils import DirManager, apply_func_parallel
		from ivas_processing_scripts.audiotools.wrappers.bs1770 import scale_files


		def logging_init(args, cfg):
		@@ -150,7 +150,13 @@ def main(args):
		# scale individual files
		if cfg.postprocessing.get("loudness", False):
		# TODO: take care of samplingrate
		scale_files(out_paths_splits, cfg.postprocessing["fmt"], cfg.postprocessing["loudness"], cfg.postprocessing.get("fs", None), out_meta_splits)
		scale_files(
		out_paths_splits,
		cfg.postprocessing["fmt"],
		cfg.postprocessing["loudness"],
		cfg.postprocessing.get("fs", None),
		out_meta_splits,
		)

		# copy configuration to output directory
		with open(cfg.output_path.joinpath(f"{cfg.name}.yml"), "w") as f:

ivas_processing_scripts/audiotools/audioarray.py

+10 −6

Original line number	Diff line number	Diff line
		@@ -42,7 +42,9 @@ logger = logging.getLogger("__main__")
		logger.setLevel(logging.DEBUG)


		### Functions used in this module
		"""Functions used in this module"""


		def trim(
		x: np.ndarray,
		fs: Optional[int] = 48000,
		@@ -183,13 +185,13 @@ def delay_compensation(
		"""

		# Get the delay in number of samples
		if flt_type == "SHQ2" and up == True:
		if flt_type == "SHQ2" and up:
		d_samples = DELAY_COMPENSATION_FOR_FILTERING["SHQ2"]["up"]
		elif flt_type == "SHQ2" and down == True:
		elif flt_type == "SHQ2" and down:
		d_samples = DELAY_COMPENSATION_FOR_FILTERING["SHQ2"]["down"]
		elif flt_type == "SHQ3" and up == True:
		elif flt_type == "SHQ3" and up:
		d_samples = DELAY_COMPENSATION_FOR_FILTERING["SHQ3"]["up"]
		elif flt_type == "SHQ3" and down == True:
		elif flt_type == "SHQ3" and down:
		d_samples = DELAY_COMPENSATION_FOR_FILTERING["SHQ3"]["down"]
		else:
		d_samples = DELAY_COMPENSATION_FOR_FILTERING[flt_type]
		@@ -405,7 +407,9 @@ def framewise_io(
		)


		### Deprecated functions (partly replaced by ITU binaries)
		"""Deprecated functions (partly replaced by ITU binaries)"""


		def resample(
		x: np.ndarray,
		in_freq: int,

ivas_processing_scripts/audiotools/binaural_datasets/binaural_dataset.py

+12 −5

Original line number	Diff line number	Diff line
		@@ -30,7 +30,6 @@
		# the United Nations Convention on Contracts on the International Sales of Goods.
		#

		import logging
		import warnings
		from pathlib import Path
		from typing import Optional, Tuple, Union
		@@ -142,15 +141,23 @@ def load_ir(
		if in_fmt == "SBA1" or in_fmt == "FOA":
		dataset_suffix = "SBA1"
		# Use truncated SBA3 dataset if no SBA1 or 2 dataset exists
		if not (Path(__file__).parent.joinpath(f"{dataset_prefix}_{dataset}_{dataset_suffix}.mat")).is_file():
		if not (
		Path(__file__).parent.joinpath(
		f"{dataset_prefix}_{dataset}_{dataset_suffix}.mat"
		)
		).is_file():
		dataset_suffix = "SBA3"
		warnings.warn(f"No SBA1 dataset found -> use truncated SBA3 dataset")
		warnings.warn("No SBA1 dataset found -> use truncated SBA3 dataset")
		elif in_fmt.endswith("2"):
		dataset_suffix = "SBA2"
		# Use truncated SBA3 dataset if no SBA1 or 2 dataset exists
		if not (Path(__file__).parent.joinpath(f"{dataset_prefix}_{dataset}_{dataset_suffix}.mat")).is_file():
		if not (
		Path(__file__).parent.joinpath(
		f"{dataset_prefix}_{dataset}_{dataset_suffix}.mat"
		)
		).is_file():
		dataset_suffix = "SBA3"
		warnings.warn(f"No SBA2 dataset found -> use truncated SBA3 dataset")
		warnings.warn("No SBA2 dataset found -> use truncated SBA3 dataset")
		else:
		dataset_suffix = "SBA3"

ivas_processing_scripts/audiotools/convert/init.py

+8 −6

Original line number	Diff line number	Diff line
		@@ -41,12 +41,12 @@ from ivas_processing_scripts.audiotools.convert.masa import convert_masa
		from ivas_processing_scripts.audiotools.convert.objectbased import convert_objectbased
		from ivas_processing_scripts.audiotools.convert.scenebased import convert_scenebased
		from ivas_processing_scripts.audiotools.wrappers.bs1770 import loudness_norm
		from ivas_processing_scripts.audiotools.wrappers.esdru import esdru
		from ivas_processing_scripts.audiotools.wrappers.filter import (
		hp50filter_itu,
		lpfilter_itu,
		resample_itu,
		)
		from ivas_processing_scripts.audiotools.wrappers.esdru import esdru
		from ivas_processing_scripts.audiotools.wrappers.p50fbmnru import p50fbmnru

		from ..metadata import write_ISM_metadata_in_file
		@@ -258,13 +258,13 @@ def process_audio(
		"""MNRU"""
		if mnru_q is not None:
		if logger:
		logger.debug(f"Applying P.50 Fullband MNRU")
		logger.debug("Applying P.50 Fullband MNRU")
		x.audio = p50fbmnru(x, mnru_q)

		"""ESDRU"""
		if esdru_alpha is not None:
		if logger:
		logger.debug(f"Applying ESDRU Recommendation ITU-T P.811")
		logger.debug("Applying ESDRU Recommendation ITU-T P.811")
		x.audio = esdru(x, esdru_alpha)

		"""limiting"""
		@@ -284,17 +284,19 @@ def format_conversion(

		# validation
		if isinstance(output, audio.MetadataAssistedSpatialAudio):
		raise NotImplementedError(f"MASA is not supported as an output for rendering!")
		raise NotImplementedError("MASA is not supported as an output for rendering!")

		if isinstance(output, audio.ObjectBasedAudio) and input.name != output.name:
		raise NotImplementedError(
		f"ISM is not supported as an output for rendering! Only usable as pass-through"
		"ISM is not supported as an output for rendering! Only usable as pass-through"
		)

		if logger:
		logger.debug(f"Format conversion: {input.name} -> {output.name}")

		if input.name == output.name or (input.name.startswith("BINAURAL") and output.name.startswith("BINAURAL")):
		if input.name == output.name or (
		input.name.startswith("BINAURAL") and output.name.startswith("BINAURAL")
		):
		output.audio = input.audio
		else:
		if isinstance(input, audio.BinauralAudio):

ivas_processing_scripts/audiotools/metadata.py

+9 −4

Original line number	Diff line number	Diff line
		@@ -413,7 +413,12 @@ def split_meta_in_file(
		# remove preamble
		if preamble:
		preamble_frames = int(preamble / IVAS_FRAME_LEN_MS)
		y = trim(audio_object.object_pos[obj], audio_object.fs, (preamble_frames, 0), samples=True)
		y = trim(
		audio_object.object_pos[obj],
		audio_object.fs,
		(preamble_frames, 0),
		samples=True,
		)
		else:
		y = audio_object.object_pos[obj]

		@@ -448,7 +453,7 @@ def check_ISM_metadata(
		path_meta = in_meta["all_items"]
		except KeyError:
		raise ValueError(
		f'Only one metadata path is given but not with key "all_items".'
		'Only one metadata path is given but not with key "all_items".'
		)

		list_meta = metadata_search(path_meta, item_names, num_objects)
		@@ -475,7 +480,7 @@ def check_ISM_metadata(
		# just read out
		list_item = current_item
		else:
		raise ValueError(f"Number of objects and metadata does not match.")
		raise ValueError("Number of objects and metadata does not match.")
		list_meta.append(list_item)
		else:
		raise ValueError("Number of metadata inputs does not match number of items")
		@@ -492,7 +497,7 @@ def metadata_search(
		"""Search for ISM metadata with structure item_name.{0-3}.csv in in_meta folder"""

		if not item_names:
		raise ValueError(f"Item names not provided, can't search for metadata")
		raise ValueError("Item names not provided, can't search for metadata")

		list_meta = []
		for item in item_names: