Commit 03065a16 authored by Anika Treffehn's avatar Anika Treffehn
Browse files

fixed preprocessing 2

parent d655ad7e

examples/TEMPLATE.yml

+23 −22
Original line number Diff line number Diff line
@@ -87,6 +87,7 @@ input: 
################################################

### Pre-processing on whole signal(s)

################################################

# preprocessing_2:

    ### Options for processing of the concatenated item (concatenate_input: true) or

    ### the individual items (concatenate_input: false) after previous pre-processing step

    ### Horizontally concatenate input items into one long file; default = false
@@ -96,9 +97,9 @@ input: 
    ### Should only be used if concatenate_input = true

    # concatenation_order: []

    ### Specify preamble duration in ms; default = 0

# preamble: 40

    # preamble: 10000

    ### Flag wheter to use noise (amplitude +-4) for the preamble or silence; default = false (silence)

# pad_noise_preamble: true

    # preamble_noise: true

    ### Additive background noise

    # background_noise:

        ### REQUIRED: SNR for background noise in dB
@@ -257,8 +258,8 @@ conditions_to_generate: 
postprocessing:

    ### REQUIRED: Target format for output

    fmt: "BINAURAL"

    ### Target sampling rate in Hz for resampling; default = null (no resampling)

    # fs: 16000

    ### REQUIRED: Target sampling rate in Hz for resampling

    fs: 48000

    ### Low-pass cut-off frequency in Hz; default = null (no filtering)

    # lp_cutoff: 24000

    ### Target loudness in LKFS; default = null (no loudness change applied)

ivas_processing_scripts/__init__.py

+6 −14
Original line number Diff line number Diff line
@@ -50,6 +50,7 @@ from ivas_processing_scripts.processing.processing import ( 
    preprocess_2,

    process_item,

    reorder_items_list,

    reverse_process_2

)

from ivas_processing_scripts.utils import DirManager, apply_func_parallel
@@ -97,7 +98,7 @@ def main(args): 


        # Re-ordering items based on concatenation order

        if hasattr(cfg, "preprocessing_2"):

            if cfg.preprocessing_2["concatenate_input"] and cfg.preprocessing_2.get("concatenation_order", None) is not None:

            if cfg.preprocessing_2.get("concatenate_input") and cfg.preprocessing_2.get("concatenation_order", None) is not None:

                cfg.items_list = reorder_items_list(cfg.items_list, cfg.preprocessing_2["concatenation_order"])



        # check for ISM metadata
@@ -128,6 +129,8 @@ def main(args): 


        # preprocessing on whole signal(s)

        if hasattr(cfg, "preprocessing_2"):

            # save process info to revert it later

            cfg.pre2 = cfg.proc_chains[0]["processes"][0]

            preprocess_2(cfg, logger)



        # run conditions
@@ -152,19 +155,8 @@ def main(args): 
                "mp" if cfg.multiprocessing else None,

            )



        if cfg.concatenate_input:

            # write out the splits, optionally remove file

            out_paths_splits, out_meta_splits = concat_teardown(cfg, logger)

            # 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,

                )

        if hasattr(cfg, "preprocessing_2"):

            reverse_process_2(cfg, logger)



    # copy configuration to output directory

    with open(cfg.output_path.joinpath(f"{cfg.name}.yml"), "w") as f:

ivas_processing_scripts/audiotools/audiofile.py

+19 −0
Original line number Diff line number Diff line
@@ -39,6 +39,7 @@ import numpy as np 
import scipy.io.wavfile as wav



from .audioarray import trim, window

from ivas_processing_scripts.audiotools import audio



logger = logging.getLogger("__main__")

logger.setLevel(logging.DEBUG)
@@ -431,3 +432,21 @@ def parse_wave_header( 
        "ext_param_size": ext_param_size,

        "ext_param": ext_param,

    }





def remove_preamble(cfg):

    # get number of channels from output format

    num_channels = audio.fromtype(cfg.postprocessing["fmt"]).num_channels

    for odir in cfg.out_dirs:

        for item in cfg.items_list:

            path_input = odir / item.name

            # read file

            x, fs = read(path_input, nchannels=num_channels, fs=cfg.postprocessing["fs"])



            # remove preamble

            x = trim(x, fs, (cfg.pre2.preamble, 0))



            # write file

            write(path_input, x, fs)



    return

ivas_processing_scripts/constants.py

+1 −0
Original line number Diff line number Diff line
@@ -89,6 +89,7 @@ REQUIRED_KEYS = [ 
    "input_path",

    "output_path",

    ("postprocessing", {"fmt"}),

    ("postprocessing", {"fs"}),

    "conditions_to_generate",

]

REQUIRED_KEYS_EVS = {"bitrates"}

ivas_processing_scripts/processing/chains.py

+5 −5
Original line number Diff line number Diff line
@@ -155,7 +155,7 @@ def get_preprocessing_2(cfg: TestConfig) -> dict: 
                "concatenate_input": pre2_cfg.get("concatenate_input", False),

                "concatenation_order": pre2_cfg.get("concatenation_order", None),

                "preamble": pre2_cfg.get("preamble", 0),

                "pad_noise_preamble": pre2_cfg.get("pad_noise_preamble", False),

                "pad_noise_preamble": pre2_cfg.get("preamble_noise", False),

                "background_noise": background,

                "in_hp50": pre2_cfg.get("hp50", False),

                "multiprocessing": cfg.multiprocessing,
@@ -246,7 +246,7 @@ def get_processing_chain( 
                    "error_pattern": cfg.tx.get("error_pattern", None),

                    "error_rate": cfg.tx.get("error_rate", None),

                    "master_seed": cfg.master_seed,

                    "prerun_seed": cfg.prerun_seed,

                    "prerun_seed": cfg.tx.get("prerun_seed", 0),

                }

            elif cfg.tx.get("type", None) == "JBM":

                tx_cfg = {
@@ -262,7 +262,7 @@ def get_processing_chain( 
        else:

            tx_cfg = None



        if hasattr(cfg, "preprocessing_2"):  # TODO: not nice

        if hasattr(cfg, "preprocessing_2"):

            preamble = cfg.preprocessing_2.get("preamble", 0)

        else:

            preamble = 0
@@ -301,7 +301,7 @@ def get_processing_chain( 
                    "error_pattern": cfg.tx.get("error_pattern", None),

                    "error_rate": cfg.tx.get("error_rate", None),

                    "master_seed": cfg.master_seed,

                    "prerun_seed": cfg.prerun_seed,

                    "prerun_seed": cfg.tx.get("prerun_seed", 0),

                }

            elif cfg.tx.get("type", None) == "JBM":

                tx_cfg = {
@@ -317,7 +317,7 @@ def get_processing_chain( 
        else:

            tx_cfg = None



        if hasattr(cfg, "preprocessing_2"):  # TODO: not nice

        if hasattr(cfg, "preprocessing_2"):

            preamble = cfg.preprocessing_2.get("preamble", 0)

        else:

            preamble = 0