Commit 14bd218d authored by Anika Treffehn's avatar Anika Treffehn
Browse files

started working on scaling after splitting

parent d3d4ab60

README.md

+1 −1
Original line number Diff line number Diff line
@@ -376,7 +376,7 @@ postprocessing: 
    ### default = null (uses postprocessing fmt if possible)

    # loudness_fmt: null

    ### Name of custom binaural dataset (without prefix or suffix);

    ### default = null (ORANGE53_Dolby for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)

    ### default = null (ORANGE53(_Dolby) for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)

    # bin_dataset: SADIE

    ### Render LFE to binaural output with the specified gain (only valid for channel-based input); default = null

    # bin_lfe_gain: 1

examples/TEMPLATE.yml

+1 −1
Original line number Diff line number Diff line
@@ -234,7 +234,7 @@ postprocessing: 
    ### default = null (uses postprocessing fmt if possible)

    # loudness_fmt: null

    ### Name of custom binaural dataset (without prefix or suffix);

    ### default = null (ORANGE53_Dolby for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)

    ### default = null (ORANGE53(_Dolby) for BINAURAL, IISofficialMPEG222UC for BINAURAL_ROOM)

    # bin_dataset: SADIE

    ### Render LFE to binaural output with the specified gain (only valid for channel-based input); default = null

    # bin_lfe_gain: 1

ivas_processing_scripts/__init__.py

+5 −1
Original line number Diff line number Diff line
@@ -49,6 +49,7 @@ 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):
@@ -145,7 +146,10 @@ def main(args): 


        if cfg.concatenate_input:

            # write out the splits, optionally remove file

            concat_teardown(cfg, logger)

            out_paths_splits, out_meta_splits = concat_teardown(cfg, logger)

            # scale individual files

            if cfg.postprocessing.get("loudness", False):

                scale_files(out_paths_splits, cfg.postprocessing["fmt"], cfg.postprocessing["loudness"], 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/audiofile.py

+4 −1
Original line number Diff line number Diff line
@@ -221,9 +221,10 @@ def split( 
    splits: list[int],

    in_fs: Optional[int] = 48000,

    preamble: Optional[int] = 0,

    loudness: Optional[float] = None,

) -> list[Union[str, Path]]:

    """

    Horizontally splits audio files into multiple shorter files and applied windowing

    Horizontally splits audio files into multiple shorter files and applies windowing and scaling



    Parameters

    __________
@@ -237,6 +238,8 @@ def split( 
        List of sample indices where to cut the signal

    in_fs: Optional[int]

        Input sampling rate, default 48000 Hz

    loudness: Optional[float]

        Desired loudness of individual files

    """



    # create a list of output files

ivas_processing_scripts/audiotools/binaural_datasets/binaural_dataset.py

+2 −1
Original line number Diff line number Diff line
@@ -129,7 +129,7 @@ def load_ir( 
    elif out_fmt.startswith("BINAURAL"):

        dataset_prefix = "HRIR"

        if dataset is None:

            dataset = "ORANGE53_Dolby"

            dataset = "ORANGE53"



        if in_fmt in OBJECT_BASED_AUDIO_FORMATS.keys() or in_fmt.startswith(

            "CUSTOM_LS"
@@ -138,6 +138,7 @@ def load_ir( 
        elif in_fmt in CHANNEL_BASED_AUDIO_FORMATS.keys() and in_fmt != "MONO":

            dataset_suffix = "LS"

        elif in_fmt in SCENE_BASED_AUDIO_FORMATS.keys():

            dataset = "ORANGE53_Dolby"

            if in_fmt == "SBA1" or in_fmt == "FOA":

                dataset_suffix = "SBA1"

                # Use truncated SBA3 dataset if no SBA1 or 2 dataset exists