nkululeko 0.94.1__py3-none-any.whl → 0.94.3__py3-none-any.whl

nkululeko/augmenting/randomsplicer.py

@@ -5,7 +5,7 @@ Code originally by Oliver Pauly
 
 Based on an idea by Klaus Scherer
 
-K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content” 
+K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content”
 Journal of Experimental Research in Personality, vol. 5, pp. 155–159, 1971.
 
 Evaluated in:

nkululeko/augmenting/randomsplicing.py

@@ -3,7 +3,7 @@ Code originally by Oliver Pauly
 
 Based on an idea by Klaus Scherer
 
-K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content” 
+K. R. Scherer, “Randomized splicing: A note on a simple technique for masking speech content”
 Journal of Experimental Research in Personality, vol. 5, pp. 155–159, 1971.
 
 Evaluated in:

nkululeko/augmenting/resampler.py

@@ -17,7 +17,7 @@ class Resampler:
     def __init__(self, df, replace, not_testing=True):
         self.SAMPLING_RATE = 16000
         self.df = df
-        self.util = Util("resampler", has_config=not_testing)
+        self.util = Util("resampler", has_config=not not_testing)
         self.util.warn(f"all files might be resampled to {self.SAMPLING_RATE}")
         self.not_testing = not_testing
         self.replace = (
@@ -30,7 +30,7 @@ class Resampler:
         files = self.df.index.get_level_values(0).values
         # replace = eval(self.util.config_val("RESAMPLE", "replace", "False"))
         replace = self.replace
-        if self.not_testing:
+        if not self.not_testing:
             store = self.util.get_path("store")
         else:
             store = "./"
@@ -67,17 +67,25 @@ class Resampler:
             self.df = self.df.set_index(
                 self.df.index.set_levels(new_files, level="file")
             )
-            target_file = self.util.config_val("RESAMPLE", "target", "resampled.csv")
-            # remove encoded labels
-            target = self.util.config_val("DATA", "target", "emotion")
-            if "class_label" in self.df.columns:
-                self.df = self.df.drop(columns=[target])
-                self.df = self.df.rename(columns={"class_label": target})
-            # save file
-            self.df.to_csv(target_file)
-            self.util.debug(
-                "saved resampled list of files to" f" {os.path.abspath(target_file)}"
-            )
+            if not self.not_testing:
+                target_file = self.util.config_val("RESAMPLE", "target", "resampled.csv")
+                # remove encoded labels
+                target = self.util.config_val("DATA", "target", "emotion")
+                if "class_label" in self.df.columns:
+                    self.df = self.df.drop(columns=[target])
+                    self.df = self.df.rename(columns={"class_label": target})
+                # save file
+                self.df.to_csv(target_file)
+                self.util.debug(
+                    "saved resampled list of files to" f" {os.path.abspath(target_file)}"
+                )
+            else:
+                # When running from command line, save to simple resampled.csv
+                target_file = "resampled.csv"
+                self.df.to_csv(target_file)
+                self.util.debug(
+                    f"saved resampled list of files to {os.path.abspath(target_file)}"
+                )
         self.util.debug(f"resampled {succes} files, {error} errors")
 
 
@@ -91,7 +99,7 @@ def main():
         df_sample.index, allow_nat=False
     )
     df_sample.head(10)
-    resampler = Resampler(df_sample, not_testing=False)
+    resampler = Resampler(df_sample, False, not_testing=False)
     resampler.resample()
     shutil.copyfile(testfile, "tmp.resample_result.wav")
     shutil.copyfile("tmp.wav", testfile)

nkululeko/autopredict/ap_age.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for age.
 Currently based on audEERING's agender model.
 """

nkululeko/autopredict/ap_arousal.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for emotional arousal.
 Currently based on audEERING's emotional dimension model.
 """

nkululeko/autopredict/ap_gender.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for biological sex.
 Currently based on audEERING's agender model.
 """

nkululeko/autopredict/ap_mos.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for MOS - mean opinion score.
 """
 

nkululeko/autopredict/ap_pesq.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for PESQ - Perceptual Evaluation of Speech Quality.
 """
 

nkululeko/autopredict/ap_sdr.py

@@ -1,6 +1,6 @@
-""""
+""" "
 A predictor for SDR - Signal to Distortion Ratio.
-as estimated by Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) 
+as estimated by Scale-Invariant Signal-to-Distortion Ratio (SI-SDR)
 """
 
 import ast

nkululeko/autopredict/ap_sid.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for sid - Speaker ID.
 """
 

nkululeko/autopredict/ap_snr.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for SNR - signal-to-noise ratio.
 """
 

nkululeko/autopredict/ap_stoi.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for STOI - Short-Time Objective Intelligibility (STOI)
 """
 

nkululeko/autopredict/ap_valence.py

@@ -1,4 +1,4 @@
-""""
+""" "
 A predictor for emotional valence.
 Currently based on audEERING's emotional dimension model.
 """

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.94.1"
+VERSION="0.94.3"
 SAMPLING_RATE = 16000

nkululeko/demo.py

@@ -7,15 +7,15 @@
 And run it in demo mode.
 It requires the project config file to be run before.
 
-Usage:  
-python -m nkululeko.demo [--config CONFIG] [--file FILE] [--list LIST] [--folder FOLDER] [--outfile OUTFILE]  
+Usage:
+python -m nkululeko.demo [--config CONFIG] [--file FILE] [--list LIST] [--folder FOLDER] [--outfile OUTFILE]
 
 Options:   \n
---config CONFIG     The base configuration file (default: exp.ini) \n  
---file FILE         A file that should be processed (16kHz mono wav) \n  
---list LIST         A file with a list of files, one per line, that should be processed (16kHz mono wav) \n  
---folder FOLDER     A name of a folder where the files within the list are in   (default: ./) \n   
---outfile OUTFILE   A filename to store the results in CSV  (default: None)  
+--config CONFIG     The base configuration file (default: exp.ini) \n
+--file FILE         A file that should be processed (16kHz mono wav) \n
+--list LIST         A file with a list of files, one per line, that should be processed (16kHz mono wav) \n
+--folder FOLDER     A name of a folder where the files within the list are in   (default: ./) \n
+--outfile OUTFILE   A filename to store the results in CSV  (default: None)
 """
 import argparse
 import configparser

nkululeko/experiment.py

@@ -1,4 +1,4 @@
-# experiment.py: Main class for an experiment (nkululeko.nkululeko)
+# nkululeko/experiment.py: Main class for an experiment (nkululeko.nkululeko)
 import ast
 import os
 import pickle
@@ -380,6 +380,7 @@ class Experiment:
             self.util.debug(
                 f"train/test shape: {self.df_train.shape}/{self.df_test.shape}"
             )
+
     def _add_random_target(self, df):
         labels = glob_conf.labels
         a = [None] * len(df)

nkululeko/feat_extract/feats_emotion2vec.py

@@ -0,0 +1,218 @@
+# feats_emotion2vec.py
+# emotion2vec feature extractor for Nkululeko
+# choices for feat_type = "emotion2vec", "emotion2vec-large", "emotion2vec-base", "emotion2vec-seed"
+
+# requirements:
+# pip install "modelscope>=1.9.5,<2.0.0"
+# pip install funasr
+
+import os
+
+import numpy as np
+import pandas as pd
+import torch
+import torchaudio
+from tqdm import tqdm
+
+import nkululeko.glob_conf as glob_conf
+from nkululeko.feat_extract.featureset import Featureset
+
+
+class Emotion2vec(Featureset):
+    """Class to extract emotion2vec embeddings."""
+
+    def __init__(self, name, data_df, feat_type):
+        """Constructor.
+
+        Is_train is needed to distinguish from test/dev sets,
+        because they use the codebook from the training.
+        """
+        super().__init__(name, data_df, feat_type)
+        # check if device is not set, use cuda if available
+        cuda = "cuda" if torch.cuda.is_available() else "cpu"
+        self.device = self.util.config_val("MODEL", "device", cuda)
+        self.model_initialized = False
+        self.feat_type = feat_type
+
+    def init_model(self):
+        # load model
+        self.util.debug("loading emotion2vec model...")
+
+        try:
+            from funasr import AutoModel
+        except ImportError:
+            self.util.error(
+                "FunASR is required for emotion2vec features. "
+                "Please install with: pip install funasr modelscope"
+            )
+
+        # Map feat_type to model names
+        model_mapping = {
+            "emotion2vec": "iic/emotion2vec_base",
+            "emotion2vec-base": "iic/emotion2vec_base_finetuned",
+            "emotion2vec-seed": "iic/emotion2vec_plus_seed",
+            "emotion2vec-large": "iic/emotion2vec_plus_large",
+        }
+
+        # Get model path from config or use default mapping
+        model_path = self.util.config_val(
+            "FEATS",
+            "emotion2vec.model",
+            model_mapping.get(self.feat_type, "iic/emotion2vec_base"),
+        )
+
+        try:
+            # Initialize the FunASR model for emotion2vec
+            self.model = AutoModel(model=model_path)
+            self.util.debug(f"initialized emotion2vec model: {model_path}")
+            self.model_initialized = True
+        except Exception as e:
+            self.util.error(f"Failed to load emotion2vec model: {str(e)}")
+
+    def extract(self):
+        """Extract the features or load them from disk if present."""
+        store = self.util.get_path("store")
+        storage = f"{store}{self.name}.pkl"
+        extract = self.util.config_val("FEATS", "needs_feature_extraction", False)
+        no_reuse = self.util.config_val("FEATS", "no_reuse", "False") == "True"
+        if extract or no_reuse or not os.path.isfile(storage):
+            if not self.model_initialized:
+                self.init_model()
+            self.util.debug(
+                "extracting emotion2vec embeddings, this might take a while..."
+            )
+            emb_series = pd.Series(index=self.data_df.index, dtype=object)
+            length = len(self.data_df.index)
+            for idx, (file, start, end) in enumerate(
+                tqdm(self.data_df.index.to_list())
+            ):
+                emb = self.extract_embedding(file, start, end)
+                emb_series.iloc[idx] = emb
+            self.df = pd.DataFrame(emb_series.values.tolist(), index=self.data_df.index)
+            self.df.to_pickle(storage)
+            try:
+                glob_conf.config["DATA"]["needs_feature_extraction"] = "false"
+            except KeyError:
+                pass
+        else:
+            self.util.debug(f"reusing extracted {self.feat_type} embeddings")
+            self.df = pd.read_pickle(storage)
+            if self.df.isnull().values.any():
+                nanrows = self.df.columns[self.df.isna().any()].tolist()
+                print(nanrows)
+                self.util.error(
+                    f"got nan: {self.df.shape} {self.df.isnull().sum().sum()}"
+                )
+
+    def extract_embedding(self, file, start, end):
+        """Extract embeddings directly from audio file."""
+        try:
+            # Handle segment extraction if needed
+            if hasattr(start, "total_seconds") and hasattr(end, "total_seconds"):
+                # Load audio segment
+                _, sampling_rate = torchaudio.load(file, frame_offset=0, num_frames=-1)
+                start_sample = int(start.total_seconds() * sampling_rate)
+                num_samples = int((end - start).total_seconds() * sampling_rate)
+                signal, sampling_rate = torchaudio.load(
+                    file, frame_offset=start_sample, num_frames=num_samples
+                )
+
+                # Resample to 16kHz if needed
+                if sampling_rate != 16000:
+                    resampler = torchaudio.transforms.Resample(sampling_rate, 16000)
+                    signal = resampler(signal)
+                    sampling_rate = 16000
+
+                # Convert to numpy and save as temporary file
+                signal_np = signal.squeeze().numpy()
+                if signal_np.ndim > 1:
+                    signal_np = signal_np[0]  # Take first channel if stereo
+
+                import tempfile
+                import soundfile as sf
+
+                with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_file:
+                    sf.write(tmp_file.name, signal_np, sampling_rate)
+                    audio_path = tmp_file.name
+            else:
+                # Use full file directly
+                audio_path = file
+
+            try:
+                # Extract features using FunASR emotion2vec model
+                res = self.model.generate(
+                    audio_path, granularity="utterance", extract_embedding=True
+                )
+
+                # Get the embeddings from the result
+                if isinstance(res, list) and len(res) > 0:
+                    embeddings = res[0].get("feats", None)
+                    if embeddings is not None:
+                        if isinstance(embeddings, list):
+                            embeddings = np.array(embeddings)
+                        return embeddings.flatten()
+                    else:
+                        # Fallback to create default embedding
+                        return np.array([0.0] * 768)
+                else:
+                    self.util.error(f"No result from emotion2vec model for file: {file}")
+                    return np.array([0.0] * 768)
+
+            finally:
+                # Clean up temporary file if we created one
+                if hasattr(start, "total_seconds") and hasattr(end, "total_seconds"):
+                    os.unlink(audio_path)
+
+        except Exception as e:
+            print(f"Error processing {file}: {str(e)}")
+            self.util.error(f"couldn't extract file: {file}, error: {str(e)}")
+            return np.array([0.0] * 768)
+
+    def extract_sample(self, signal, sr):
+        """Extract features from a single sample."""
+        if not self.model_initialized:
+            self.init_model()
+        
+        # Save signal as temporary file for emotion2vec
+        import tempfile
+        import soundfile as sf
+        
+        try:
+            # Convert tensor to numpy if needed
+            if torch.is_tensor(signal):
+                signal_np = signal.squeeze().numpy()
+            else:
+                signal_np = signal.squeeze()
+                
+            # Handle multi-channel audio
+            if signal_np.ndim > 1:
+                signal_np = signal_np[0]
+                
+            with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_file:
+                sf.write(tmp_file.name, signal_np, sr)
+                
+                # Extract using the emotion2vec model
+                res = self.model.generate(
+                    tmp_file.name, granularity="utterance", extract_embedding=True
+                )
+                
+                # Get embeddings from result
+                if isinstance(res, list) and len(res) > 0:
+                    embeddings = res[0].get("feats", None)
+                    if embeddings is not None:
+                        if isinstance(embeddings, list):
+                            embeddings = np.array(embeddings)
+                        return embeddings.flatten()
+                
+                return np.array([0.0] * 768)
+                
+        except Exception as e:
+            print(f"Error in extract_sample: {str(e)}")
+            return np.array([0.0] * 768)
+        finally:
+            # Clean up temporary file
+            if tmp_file is not None:  # Check if tmp_file was created
+                try:
+                    os.unlink(tmp_file.name)
+                except:
+                    pass

nkululeko/feat_extract/feats_mos.py

@@ -1,11 +1,11 @@
-""" feats_mos.py
+"""feats_mos.py
 predict MOS (mean opinion score)
 
 adapted from
 from https://pytorch.org/audio/main/tutorials/squim_tutorial.html#sphx-glr-tutorials-squim-tutorial-py
 paper: https://arxiv.org/pdf/2304.01448.pdf
 
-needs 
+needs
 pip uninstall -y torch torchvision torchaudio
 pip install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu
 

nkululeko/feat_extract/feats_snr.py

@@ -1,4 +1,4 @@
-""" feats_snr.py is to estimate snr.
+"""feats_snr.py is to estimate snr.
 
 SNR (signal to noise ratio) is extracted as acoustic features.
 """

nkululeko/feature_extractor.py

@@ -1,6 +1,6 @@
 """Extract acoustic features from audio samples.
 
-Extract acoustic features using several feature extractors 
+Extract acoustic features using several feature extractors
 (appends the features column-wise)
 """
 
@@ -75,7 +75,7 @@ class FeatureExtractor:
             return TRILLset
 
         elif feats_type.startswith(
-            ("wav2vec2", "hubert", "wavlm", "spkrec", "whisper", "ast")
+            ("wav2vec2", "hubert", "wavlm", "spkrec", "whisper", "ast", "emotion2vec")
         ):
             return self._get_feat_extractor_by_prefix(feats_type)
 

nkululeko/models/model.py

@@ -3,11 +3,15 @@ import ast
 import pickle
 import random
 
+from joblib import parallel_backend
 import numpy as np
 import pandas as pd
+from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import LeaveOneGroupOut
+from sklearn.model_selection import StratifiedKFold
 import sklearn.utils
-from joblib import parallel_backend
-from sklearn.model_selection import GridSearchCV, LeaveOneGroupOut, StratifiedKFold
+
+import audeer
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.reporter import Reporter
@@ -301,8 +305,15 @@ class Model:
     def get_type(self):
         return "generic"
 
-    def predict_sample(self, features):
-        """Predict one sample"""
+    def predict_sample(self, features: np.ndarray) -> dict | float:
+        """Predict a single sample using the trained model.
+
+        Args:
+            features (np.ndarray): The feature vector of the sample to predict.
+
+        Returns:
+            dict: A dictionary containing the predicted class probabilities or value.
+        """
         prediction = {}
         if self.util.exp_is_classification():
             # get the class probabilities
@@ -336,3 +347,30 @@ class Model:
         self.set_id(run, epoch)
         with open(path, "rb") as handle:
             self.clf = pickle.load(handle)
+
+    # next function exports the model to onnx
+    def export_onnx(self, onnx_path, input_shape=None):
+        """Export the trained sklearn model to ONNX format.
+
+        Args:
+            onnx_path (str): Path to save the ONNX model.
+            input_shape (tuple, optional): Shape of the input features. If None, inferred from feats_train.
+        """
+        import skl2onnx
+        from skl2onnx import convert_sklearn
+        from skl2onnx.common.data_types import FloatTensorType
+
+        if not hasattr(self, "clf"):
+            self.util.error("No trained model found to export.")
+            return
+
+        if input_shape is None:
+            n_features = self.feats_train.shape[1]
+            initial_type = [("input", FloatTensorType([None, n_features]))]
+        else:
+            initial_type = [("input", FloatTensorType(input_shape))]
+
+        onnx_model = convert_sklearn(self.clf, initial_types=initial_type)
+        with open(audeer.path(onnx_path), "wb") as f:
+            f.write(onnx_model.SerializeToString())
+        self.util.debug(f"Model exported to ONNX at {onnx_path}")

nkululeko/models/model_cnn.py

@@ -1,4 +1,4 @@
-""" 
+"""
 model_cnn.py
 
 Inspired by code from Su Lei

nkululeko/models/model_xgb.py

@@ -1,4 +1,4 @@
-# xgbmodel.py
+# model_xgb.py
 
 from xgboost import XGBClassifier
 

nkululeko/models/tests/test_model_svm.py

@@ -0,0 +1,56 @@
+import os
+
+import numpy as np
+import pandas as pd
+import pytest
+
+from nkululeko.models.model_svm import SVM_model
+
+
+@pytest.fixture(scope="module")
+def polish_data():
+    data_dir = os.path.abspath("data/polish")
+    train_csv = os.path.join(data_dir, "polish_train.csv")
+    test_csv = os.path.join(data_dir, "polish_test.csv")
+    # Load a small sample for speed
+    df_train = pd.read_csv(train_csv).head(10)
+    df_test = pd.read_csv(test_csv).head(5)
+    # Assume 'file' and 'emotion' columns exist
+    # Mock features: random floats, shape (n_samples, n_features)
+    feats_train = np.random.rand(len(df_train), 10)
+    feats_test = np.random.rand(len(df_test), 10)
+    return df_train, df_test, feats_train, feats_test
+
+
+def test_svm_model_init(polish_data):
+    df_train, df_test, feats_train, feats_test = polish_data
+    model = SVM_model(df_train, df_test, feats_train, feats_test)
+    assert model.name == "svm"
+    assert hasattr(model, "clf")
+    assert model.is_classifier
+
+
+def test_svm_model_fit_and_predict(polish_data):
+    df_train, df_test, feats_train, feats_test = polish_data
+    model = SVM_model(df_train, df_test, feats_train, feats_test)
+    # Fit the model
+    y_train = df_train["emotion"].astype(str)
+    model.clf.fit(feats_train, y_train)
+    # Predict
+    preds = model.clf.predict(feats_test)
+    assert len(preds) == feats_test.shape[0]
+
+
+def test_svm_model_set_c(polish_data):
+    df_train, df_test, feats_train, feats_test = polish_data
+    model = SVM_model(df_train, df_test, feats_train, feats_test)
+    old_c = model.clf.C
+    model.set_c(2.0)
+    assert model.clf.C == 2.0
+    assert model.clf.C != old_c
+
+
+def test_svm_model_get_type(polish_data):
+    df_train, df_test, feats_train, feats_test = polish_data
+    model = SVM_model(df_train, df_test, feats_train, feats_test)
+    assert model.get_type() == "svm"

nkululeko/nkululeko.py

@@ -1,5 +1,7 @@
-# nkululeko.py
-# Entry script to do a Nkululeko experiment
+#!/usr/bin/env python3
+
+# nkululeko.py: Entry script to do a Nkululeko experiment
+
 import argparse
 import configparser
 from pathlib import Path
@@ -52,6 +54,15 @@ def doit(config_file):
     reports, last_epochs = expr.run()
     result = expr.get_best_report(reports).result.test
     expr.store_report()
+
+    # check if we want to export the model
+    o_path = util.config_val("EXP", "export_onnx", "False")
+    if eval(o_path):
+        print(f"Exporting ONNX model to {o_path}")
+        o_path = o_path.replace('"', '')
+        expr.runmgr.get_best_model().export_onnx(str(o_path))
+
+
     print("DONE")
     return result, int(np.asarray(last_epochs).min())
 

nkululeko/reporting/report_item.py

@@ -1,4 +1,4 @@
-""" reportitem.py
+"""reportitem.py
 a basic report snippet.
 """
 

nkululeko/runmanager.py

@@ -1,6 +1,6 @@
 """Runmanager module.
 
-This module contains the Runmanager class which is responsible for managing the 
+This module contains the Runmanager class which is responsible for managing the
 runs of the experiment.
 """
 
@@ -22,8 +22,9 @@ class Runmanager:
     )  # The dataframes
     reports = []
 
-    def __init__(self, df_train, df_test, feats_train,
-                 feats_test, dev_x=None, dev_y=None):
+    def __init__(
+        self, df_train, df_test, feats_train, feats_test, dev_x=None, dev_y=None
+    ):
         """Constructor setting up the dataframes.
 
         Args:
@@ -115,13 +116,23 @@ class Runmanager:
                 + f"_BEST-dev_{best_report.run}_{best_report.epoch:03d}"
             )
             # finally, print out the numbers for this run
-            self.print_report(best_report, plot_name)
+            # self.print_report(best_report, plot_name)
+            # remember the best run
+            # Only print if best_report is not the same as last_report
+            if best_report is not last_report:
+                plot_name = (
+                    self.util.config_val("PLOT", "name", plot_name_suggest)
+                    + f"_BEST-dev_{best_report.run}_{best_report.epoch:03d}"
+                )
+                self.print_report(best_report, plot_name)
+
             self.best_results.append(best_report)
             self.last_epochs.append(last_epoch)
             if self.split3:
                 best_model = self.get_best_model()
                 self.test_report = self.modelrunner.eval_specific_model(
-                    best_model, self.df_test, self.feats_test)
+                    best_model, self.df_test, self.feats_test
+                )
                 self.test_report.epoch = best_report.epoch
                 plot_name = (
                     self.util.config_val("PLOT", "name", plot_name_suggest)
@@ -170,12 +181,11 @@ class Runmanager:
         """
         # self.load_model(report)
         # report = self.model.predict()
-        self.util.debug(f"plotting conf matrix to {plot_name}")
-        report.plot_confmatrix(plot_name, epoch = report.epoch)
-        report.print_results(report.epoch, file_name = plot_name)
+        self.util.debug(f"plotting conf matrix as {plot_name}")
+        report.plot_confmatrix(plot_name, epoch=report.epoch)
+        report.print_results(report.epoch, file_name=plot_name)
         report.print_probabilities(file_name=plot_name)
 
-
     def load_model(self, report):
         """Load a model from disk for a specific run and epoch and evaluate it.
 

nkululeko/scaler.py

@@ -11,17 +11,24 @@ class Scaler:
     """Class to normalize speech features."""
 
     def __init__(
-        self, train_data_df, test_data_df, train_feats, test_feats, scaler_type, dev_x = None, dev_y = None
+        self,
+        train_data_df,
+        test_data_df,
+        train_feats,
+        test_feats,
+        scaler_type,
+        dev_x=None,
+        dev_y=None,
     ):
         """Constructor.
 
-            Parameters:
-                    train_data_df (pd.DataFrame): The training dataframe with speakers.
-                        only needed for speaker normalization
-                    test_data_df (pd.DataFrame): The test dataframe with speakers
-                        only needed for speaker normalization
-                    train_feats (pd.DataFrame): The train features dataframe
-                    test_feats (pd.DataFrame): The test features dataframe (can be None)
+        Parameters:
+                train_data_df (pd.DataFrame): The training dataframe with speakers.
+                    only needed for speaker normalization
+                test_data_df (pd.DataFrame): The test dataframe with speakers
+                    only needed for speaker normalization
+                train_feats (pd.DataFrame): The train features dataframe
+                test_feats (pd.DataFrame): The test features dataframe (can be None)
         """
         self.util = Util("scaler")
         if scaler_type == "standard":
@@ -45,12 +52,13 @@ class Scaler:
         else:
             self.feats_dev = None
             self.data_dev = None
+
     def scale(self):
         """Actually scales/normalizes.
 
-            Returns:
-                    train_feats (pd.DataFrame): The scaled train features dataframe
-                    test_feats (pd.DataFrame): The scaled test features dataframe (can be None)
+        Returns:
+                train_feats (pd.DataFrame): The scaled train features dataframe
+                test_feats (pd.DataFrame): The scaled test features dataframe (can be None)
         """
         if self.scaler_type != "speaker":
             self.util.debug("scaling features based on training set")
@@ -66,7 +74,7 @@ class Scaler:
             if self.feats_test is not None:
                 self.feats_test = self.scale_df(self.feats_test)
             if self.feats_dev is not None:
-                self.feats_dev = self.scale_df(self.feats_dev)  
+                self.feats_dev = self.scale_df(self.feats_dev)
         else:
             self.bin_to_three()
         if self.feats_dev is not None:
@@ -84,8 +92,8 @@ class Scaler:
         if self.feats_test is not None:
             self.feats_test = self.speaker_scale_df(self.data_test, self.feats_test)
         if self.feats_dev is not None:
-                self.feats_dev = self.speaker_scale_df(self.data_dev, self.feats_dev)
-                return [self.feats_train, self.feats_dev, self.feats_test]
+            self.feats_dev = self.speaker_scale_df(self.data_dev, self.feats_dev)
+            return [self.feats_train, self.feats_dev, self.feats_test]
         else:
             return [self.feats_train, self.feats_test]
 

nkululeko/test_predictor.py

@@ -1,6 +1,6 @@
 """test_predictor.py.
 
-    Predict targets from a model and save as csv file.
+Predict targets from a model and save as csv file.
 
 """
 

nkululeko/utils/unzip.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+
+# unzip.py - Extracts all files from the specified zip files (in case unzip is not installed).
+# usage: python unzip.py file1.zip file2.zip ...
+# source: https://askubuntu.com/questions/86849/how-to-unzip-a-zip-file-from-the-terminal
+
+# mimics the unzip command
+# # To extract an archive to a specific directory:
+# unzip <archive>.zip -d <directory>
+
+import argparse
+from zipfile import ZipFile
+
+# Set up argument parser
+parser = argparse.ArgumentParser(description="Extract files from zip archives.")
+parser.add_argument("zip_files", nargs="+", help="List of zip files to extract.")
+parser.add_argument(
+    "-d",
+    "--directory",
+    default=".",
+    help="Directory to extract files to (default: current directory).",
+)
+args = parser.parse_args()
+
+# Extract arguments
+directory = args.directory
+zip_files = args.zip_files
+
+# Process each zip file
+for zip_file in zip_files:
+    try:
+        with ZipFile(zip_file) as zf:
+            zf.extractall(path=directory)
+        print(f"Extracting {zip_file} to {directory}")
+    except FileNotFoundError:
+        print(f"Error: File {zip_file} not found")
+    except Exception as e:
+        print(f"Error extracting {zip_file}: {e}")

nkululeko/utils/util.py

@@ -30,6 +30,7 @@ class Util:
     ]
 
     def __init__(self, caller=None, has_config=True):
+        self.logger = None
         if caller is not None:
             self.caller = caller
         else:
@@ -48,7 +49,12 @@ class Util:
                         self.error(f"no such file: {self.got_data_roots}")
                     self.data_roots = configparser.ConfigParser()
                     self.data_roots.read(self.got_data_roots)
-            except (ModuleNotFoundError, AttributeError):
+            except ModuleNotFoundError as e:
+                self.error(e)
+                self.config = None
+                self.got_data_roots = False
+            except AttributeError as e:
+                self.error(e)
                 self.config = None
                 self.got_data_roots = False
 
@@ -311,14 +317,22 @@ class Util:
         return False
 
     def error(self, message):
-        self.logger.error(f"ERROR: {self.caller}: {message}")
+        if self.logger is not None:
+            self.logger.error(f"ERROR: {self.caller}: {message}")
+        else:
+            print(f"ERROR: {message}")
         sys.exit()
 
     def warn(self, message):
-        self.logger.warning(f"WARNING: {self.caller}: {message}")
-
+        if self.logger is not None:
+            self.logger.warning(f"WARNING: {self.caller}: {message}")
+        else:
+            print(f"WARNING: {message}")
     def debug(self, message):
-        self.logger.debug(f"DEBUG: {self.caller}: {message}")
+        if self.logger is not None:
+            self.logger.debug(f"DEBUG: {self.caller}: {message}")
+        else:
+            print(f"DEBUG: {message}")
 
     def set_config_val(self, section, key, value):
         try:

nkululeko-0.94.3.dist-info/METADATA

@@ -0,0 +1,76 @@
+Metadata-Version: 2.4
+Name: nkululeko
+Version: 0.94.3
+Summary: Machine learning audio prediction experiments based on templates
+Home-page: https://github.com/felixbur/nkululeko
+Author: Felix Burkhardt
+Author-email: fxburk@gmail.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 3 - Alpha
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+License-File: LICENSE
+Requires-Dist: audeer>=1.0.0
+Requires-Dist: audformat>=1.3.1
+Requires-Dist: audinterface>=1.0.0
+Requires-Dist: audiofile>=1.0.0
+Requires-Dist: audiomentations==0.31.0
+Requires-Dist: audmetric>=1.0.0
+Requires-Dist: audonnx>=0.7.0
+Requires-Dist: confidence-intervals>=0.0.2
+Requires-Dist: datasets>=2.0.0
+Requires-Dist: imageio>=2.0.0
+Requires-Dist: matplotlib>=3.0.0
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: opensmile>=2.0.0
+Requires-Dist: pandas>=1.0.0
+Requires-Dist: praat-parselmouth>=0.4.0
+Requires-Dist: scikit_learn>=1.0.0
+Requires-Dist: scipy>=1.0.0
+Requires-Dist: seaborn>=0.11.0
+Requires-Dist: sounddevice>=0.4.0
+Requires-Dist: transformers>=4.0.0
+Requires-Dist: umap-learn>=0.5.0
+Requires-Dist: xgboost>=1.0.0
+Requires-Dist: pylatex>=1.0.0
+Provides-Extra: torch
+Requires-Dist: torch>=1.0.0; extra == "torch"
+Requires-Dist: torchvision>=0.10.0; extra == "torch"
+Requires-Dist: torchaudio>=0.10.0; extra == "torch"
+Provides-Extra: torch-cpu
+Requires-Dist: torch>=1.0.0; extra == "torch-cpu"
+Requires-Dist: torchvision>=0.10.0; extra == "torch-cpu"
+Requires-Dist: torchaudio>=0.10.0; extra == "torch-cpu"
+Provides-Extra: torch-nightly
+Requires-Dist: torch; extra == "torch-nightly"
+Requires-Dist: torchvision; extra == "torch-nightly"
+Requires-Dist: torchaudio; extra == "torch-nightly"
+Provides-Extra: spotlight
+Requires-Dist: renumics-spotlight>=1.6.13; extra == "spotlight"
+Requires-Dist: sliceguard>=0.0.35; extra == "spotlight"
+Provides-Extra: tensorflow
+Requires-Dist: tensorflow>=2.0.0; extra == "tensorflow"
+Requires-Dist: tensorflow_hub>=0.12.0; extra == "tensorflow"
+Provides-Extra: all
+Requires-Dist: torch>=1.0.0; extra == "all"
+Requires-Dist: torchvision>=0.10.0; extra == "all"
+Requires-Dist: torchaudio>=0.10.0; extra == "all"
+Requires-Dist: renumics-spotlight>=0.1.0; extra == "all"
+Requires-Dist: sliceguard>=0.1.0; extra == "all"
+Requires-Dist: tensorflow>=2.0.0; extra == "all"
+Requires-Dist: tensorflow_hub>=0.12.0; extra == "all"
+Requires-Dist: shap>=0.40.0; extra == "all"
+Requires-Dist: imblearn>=0.0.0; extra == "all"
+Requires-Dist: cylimiter>=0.0.1; extra == "all"
+Requires-Dist: audtorch>=0.0.1; extra == "all"
+Requires-Dist: splitutils>=0.0.1; extra == "all"
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

{nkululeko-0.94.1.dist-info → nkululeko-0.94.3.dist-info}/RECORD

@@ -1,17 +1,18 @@
+examples/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=wpiHCJ7zsW38kumg3ypwXZe2HQrhUblAnv7P2QeJnAc,3525
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=4_cPNkLfZWa0md1LsHb3_P28dE2j0zAcBid8gDk0hsY,39
+nkululeko/constants.py,sha256=KCqkmtwj--gcAdaRwj_Zb44_ewVNp06Hfp8-YGDG8iI,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
-nkululeko/demo.py,sha256=4Yzhg6pCPBYPGJrP7JX2TysVosl_R1llpVDKc2P_gUA,4955
+nkululeko/demo.py,sha256=tu7Al2l5MCLVegkDC-NE2wcuc_YE7NRbgOlPW3yhGEs,4940
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
 nkululeko/demo_predictor.py,sha256=lDF-xOxRdEAclOmbepAYg-BQXQdGkHfq2n74PTIoop8,4872
 nkululeko/ensemble.py,sha256=71V-rre61H3J4sh7lu-OTo4I2_g7mm_rQxwW1ARDHgY,12782
-nkululeko/experiment.py,sha256=ywswsCdSDUQLWIHn055wT1N40hFBSBUB3NnS5Hq6aMk,36210
+nkululeko/experiment.py,sha256=xZQ3SpFhH4QByRzVBCO4Ps84KDXKuVPZ_qUzLUPgN5g,36221
 nkululeko/explore.py,sha256=FPM2CS-LKgcDV-LnjYlD6pEv7HuCQpH_C3KyyiOCdk4,3589
 nkululeko/export.py,sha256=U-V4acxtuL6qKt6oAsVcM5TTeWogYUJ3GU-lA6rq6d4,4336
-nkululeko/feature_extractor.py,sha256=UnspIWz3XrNhKnBBhWZkH2bHvD-sROtrQVqB1JvkUyw,4088
+nkululeko/feature_extractor.py,sha256=X6ZWDjGwUMVwnP6TkCEnw8B4xo8eWvJa1QT9-0WUuvA,4102
 nkululeko/file_checker.py,sha256=xJY0Q6w47pnmgJVK5rcAKPYBrCpV7eBT4_3YBzTx-H8,3454
 nkululeko/filter_data.py,sha256=4sGrKvMZ_hLnJPrHm_CqjDPKIRV8REWoT7nfSYGXbwo,7305
 nkululeko/fixedsegment.py,sha256=Tb92QiuiyMsOO3WRWwuGjZGibS8hbHHCrcWAXGk7g04,2868
@@ -19,34 +20,34 @@ nkululeko/glob_conf.py,sha256=KL9YJQTHvTztxo1vr25qRRgaPnx4NTg0XrdbovKGMmw,525
 nkululeko/modelrunner.py,sha256=NpDgXfKkn8dOrQzhUiEfGI56Qrb1sOtWTD31II4Zgbk,11550
 nkululeko/multidb.py,sha256=sO6OwJn8sn1-C-ig3thsIL8QMWHdV9SnJhDodKjeKrI,6876
 nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
-nkululeko/nkululeko.py,sha256=0RMce-dOyt7ldvo5pHGTL5R7H5NPPVklhMtRmWoZh1I,1952
+nkululeko/nkululeko.py,sha256=FaLimlbx47rJgWgDEd0ZROAiXy2cOypliVdqJn-Bvws,2257
 nkululeko/plots.py,sha256=i9VIkviBWLgncfnyK44TUMzg2Xa0_UhfL0LnMF1vHTw,27022
 nkululeko/predict.py,sha256=MLnHEyFmSiHLLs-HDczag8Vu3zKF5T1rXLKdZZJ6py8,2083
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
-nkululeko/runmanager.py,sha256=2jAUsWA5A13xTwEb4M3TmGLJsAUAZB2i4K41F6AAZYo,8478
-nkululeko/scaler.py,sha256=D3x4waIfTqt1vGBKd__uJslyss1kSNd9BUtj4_4eG_8,5105
+nkululeko/runmanager.py,sha256=YtGQP0UyyQTKkilncB1XYM-T8oatzGcZEOcj5SorjJw,8902
+nkululeko/scaler.py,sha256=a4lKwWT436TV4VEvqtP1uQ58Yz67XVHr1HjO5gp3xLI,5109
 nkululeko/segment.py,sha256=7UrJEwdLmh9wDL5iBwpdJyJm9dwSxidHrHt-_D2qtxw,4949
 nkululeko/syllable_nuclei.py,sha256=5w_naKxNxz66a_qLkraemi2fggM-gWesiiBPS47iFcE,9931
 nkululeko/test.py,sha256=1w624vo5KTzmFC8BUStGlLDmIEAFuJUz7J0W-gp7AxI,1677
-nkululeko/test_predictor.py,sha256=DEHE_D3A6m6KJTrpDKceA1n655t_UZV3WQd57K4a3Ho,2863
+nkululeko/test_predictor.py,sha256=RPQxorj1uygLeSnAuNims5CFccXwrDwTnrIDs-gDlNQ,2859
 nkululeko/test_pretrain.py,sha256=6FZeETlWzg9Cq_sn3BFKhfH91jW26nAIDm1bJkInNNA,8463
 nkululeko/augmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/augmenting/augmenter.py,sha256=TUUznEz0pe9DSMC9r7LoBckuvsJTprvypeV5-8zLn20,2846
-nkululeko/augmenting/randomsplicer.py,sha256=TKPqp8np5dvyJIAjOTvtlanatFQ9OwKxZ02QoCwZ2Jw,2802
-nkululeko/augmenting/randomsplicing.py,sha256=RUwYukqDUbRqs_hD2wYPL6g2nLFhjCuPVbJ6qx3VzU8,1751
-nkululeko/augmenting/resampler.py,sha256=gcjyyTD6QtJK6s_xoOQpsu5adpn0uSJwHxJTHMskfOM,3541
+nkululeko/augmenting/randomsplicer.py,sha256=TQTy4RBt6XbWiuUu5Ic913DMvmwTUwEufldBJjo7i1s,2801
+nkululeko/augmenting/randomsplicing.py,sha256=GXCpCDdOsOyWACDJ3ujmFZBVe6ISvkoQLefBNPgxxow,1750
+nkululeko/augmenting/resampler.py,sha256=j2yuB9h9UwGQHqwF8CZPSGqAfOiyQV3979WQjU2toVM,3962
 nkululeko/autopredict/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/autopredict/ap_age.py,sha256=SaD8-WWBLjb4x2jxIsU-_uvlYxcE0YhxUOnh9PAYTiU,1097
-nkululeko/autopredict/ap_arousal.py,sha256=unKN9VefJ_eesUqy1YTMSvYs1kBMQP1HBZI6cY0En6c,1026
+nkululeko/autopredict/ap_age.py,sha256=yzd8sF6gi0hnqNawyLBCIkt-pKgl9gYPlZHsrLGfz0U,1098
+nkululeko/autopredict/ap_arousal.py,sha256=lpv3jTSVEVCcR226JevNM6S7e0_uMZXHb_8Wpup1yj8,1027
 nkululeko/autopredict/ap_dominance.py,sha256=Ltq5x0ralxU1758_e-nNKvzexiPUM66xLAm3Wo2B07c,1040
-nkululeko/autopredict/ap_gender.py,sha256=b6oTqHKVwOnYh4YlKbuMflssS4HJqs_c1ayusauY_I4,1010
-nkululeko/autopredict/ap_mos.py,sha256=e4hmgb0Yf1_AbC5P0CqXJIvufjhbTrqmI5goARxrY0Y,1107
-nkululeko/autopredict/ap_pesq.py,sha256=mRt3Loucaoy4vJxwfuxUt0fP88bMGvkmrLCEpKEXWp0,1140
-nkululeko/autopredict/ap_sdr.py,sha256=VQ2UkxOO3ipqYNNjFwKgEaGCk8IzLI5lX_2tZFLIvTY,1188
-nkululeko/autopredict/ap_sid.py,sha256=mCxf2DUOPUlDdnVwCeljFJtCXM4uum1poZQ9RrwHHM8,2641
-nkululeko/autopredict/ap_snr.py,sha256=AiTU8-7CMEeowmYkMO19lw1HCb1yTXC6KeulNf8gOqw,1110
-nkululeko/autopredict/ap_stoi.py,sha256=UEQg1ZV0meAsxgdWB8ieRs9GPXHqArmsaOyCGRwpcnA,1187
-nkululeko/autopredict/ap_valence.py,sha256=WrW4Ltqi_odW49_4QEVKkfnrcztLIVZ4cXIEHu4dBN8,1026
+nkululeko/autopredict/ap_gender.py,sha256=RjLv9YxY9OPHT_gnd6htjKQzQA4DSKcbjipKGjHHx2A,1011
+nkululeko/autopredict/ap_mos.py,sha256=PMLU67JDgYQMobRSR2vW9cWoL3QK5JbhLM65fVsRGkc,1108
+nkululeko/autopredict/ap_pesq.py,sha256=EuJ9u6oaSPWdYsaU8q3t8tiFKhfW1qdqgO-cySpfxw0,1141
+nkululeko/autopredict/ap_sdr.py,sha256=xYCy4M_aWzoFiYD_KOK9ys2P2v0bfxNkLcIRdi5z2h4,1188
+nkululeko/autopredict/ap_sid.py,sha256=b_JwVWlqcwdC7acU9Q7mExuOJKUn6qdlmQTm8pmmptk,2642
+nkululeko/autopredict/ap_snr.py,sha256=cjc0pUsCN_RacTw1UBR2cGY9t_um48f2cjo3QJDn7bw,1111
+nkululeko/autopredict/ap_stoi.py,sha256=csv9qCcRmieHAhypszqGoGt9r3biM8IYPgcTwp9GIFM,1188
+nkululeko/autopredict/ap_valence.py,sha256=9S06SpO_zXKSpkf0InHYYXZcD9HDGoCJ6UPkn__eBAg,1027
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
 nkululeko/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/data/dataset.py,sha256=JLbBYGniUrjwxs-HtbIyhqO3Cv-ELfpmlq7jzij4dBc,41759
@@ -59,15 +60,16 @@ nkululeko/feat_extract/feats_ast.py,sha256=w62xEoLiFtU-rj6SXkqXAktmoFaXcAcAWpUyE
 nkululeko/feat_extract/feats_auddim.py,sha256=CGLp_aYhudfwoU5522vjrvjPxfZcyw593A8xLjYefV8,3134
 nkululeko/feat_extract/feats_audmodel.py,sha256=OsZyB1rdcG0Fai2gAwBlbuubmWor1_-P4IDkZLqgPKE,3161
 nkululeko/feat_extract/feats_clap.py,sha256=1tttpfm2SJmQgYm2u8eUVpDiDOpWdKqFChpY3ZZokNs,3395
+nkululeko/feat_extract/feats_emotion2vec.py,sha256=ObVlqbsJsw-hWGsUOXY68Ebynt5Bn4Xtlu_Gvq3XJI4,8728
 nkululeko/feat_extract/feats_hubert.py,sha256=F3vrPCkx8EimJjFWYCZ7Yg9uo1G3NjYt4UKrGIUev8k,5172
 nkululeko/feat_extract/feats_import.py,sha256=cPi4XRuRs71npB8YGXr7rYOvkeTU_oZEl3GrGncdiqY,2222
 nkululeko/feat_extract/feats_mld.py,sha256=5aRoYiGDm5ApoFntxAMQYPjEelXHHRBHZcAJR9dxaeI,1945
-nkululeko/feat_extract/feats_mos.py,sha256=3UXCKe86F49yHpZMQnLfDWXx9XdmlXHOy8efoa3WaOk,4138
+nkululeko/feat_extract/feats_mos.py,sha256=vkH1FdXtduoU0-yjBtVccC2b_p_eyH8laRnwlL7QTVM,4136
 nkululeko/feat_extract/feats_opensmile copy.py,sha256=BLj5sUaBPz7vLPfNlt9LdQurSypmViqgSpPK-6aXGhQ,4029
 nkululeko/feat_extract/feats_opensmile.py,sha256=HwbGs0EaPxZ7DznQZFem8RYgyQWz02oya77uVY7KhZE,9203
 nkululeko/feat_extract/feats_oxbow.py,sha256=TRoEJx5EKZiqoPoPRibHc0vkBMoZcKlGoGNq4NbyHZw,4895
 nkululeko/feat_extract/feats_praat.py,sha256=jZ-XXbP3iy25QQIzA4Hrv0HxsYvJNPavoCW2FyJNKMg,3064
-nkululeko/feat_extract/feats_snr.py,sha256=5uEm10d89TQPf0s-CuVpQ3ftc0bLEeuB8aGuufsjAbs,2762
+nkululeko/feat_extract/feats_snr.py,sha256=Zxwo78HLleNsziYLOj34RQUnp9I7r1yMXqjYipDOjZw,2761
 nkululeko/feat_extract/feats_spectra.py,sha256=6WhFUpB0WTutg7OFMlAw9lSwVU5OBYCDcPRxaiH-Qn8,3621
 nkululeko/feat_extract/feats_spkrec.py,sha256=o_6bdU4lIkj64S5Kdjf1iyuo1VASeYxE4XdxV94a8gE,4732
 nkululeko/feat_extract/feats_squim.py,sha256=yJifsp9kj9iJjW_UAKr3LlvVhX5rv7el4bepn0wN2a8,4578
@@ -82,9 +84,9 @@ nkululeko/losses/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 nkululeko/losses/loss_ccc.py,sha256=NOK0y0fxKUnU161B5geap6Fmn8QzoPl2MqtPiV8IuJE,976
 nkululeko/losses/loss_softf1loss.py,sha256=5gW-PuiqeAZcRgfwjueIOQtMokOjZWgQnVIv59HKTCo,1309
 nkululeko/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nkululeko/models/model.py,sha256=2STBD3jtLKeNSk7arCFJdaV6FL-nuLR1qpsjvZ4W-9A,12975
+nkululeko/models/model.py,sha256=0O6H-kME1yVHU-EKu5iOZVBB7fFNg3lfagvGgMrldxM,14426
 nkululeko/models/model_bayes.py,sha256=tQUXEsXoS6WnfapQjP78S_gxNBssTOqE78A2iG8SfLU,407
-nkululeko/models/model_cnn.py,sha256=lu6ZSGqJBL69PdrgwwgzjGmu_DaBaiATkz6oVqQpKhc,10498
+nkululeko/models/model_cnn.py,sha256=TKj43865epsiK7a0COyfBDaFHKOYgWgnPpMVCPWUhCM,10497
 nkululeko/models/model_gmm.py,sha256=mhHFNtTzHuJvqYSA0h5YhvjA--KhnN6MTU_S0G3-d1c,1332
 nkululeko/models/model_knn.py,sha256=ByQlHIU_fNtSCGCvsrMEoLVJ9q2hUC4edtpp5rVS1B8,600
 nkululeko/models/model_knn_reg.py,sha256=kaVP1xGNgktUGuQARi7uoJ0hmdPGHDpv2ugDesYN7RU,611
@@ -96,13 +98,15 @@ nkululeko/models/model_svr.py,sha256=FEwYRdgqwgGhZdkpRnT7Ef12lklWi6GZL28PyV99xWs
 nkululeko/models/model_tree.py,sha256=6L3PD3aIiiQz1RPWS6z3Edx4f0gnR7AOfBKOJzf0BNU,433
 nkululeko/models/model_tree_reg.py,sha256=IMaQpNImoRqP8Biw1CsJevxpV_PVpKblsKtYlMW5d_U,429
 nkululeko/models/model_tuned.py,sha256=VuRyNqw3XTpQ2eHsWOJN8X-V98AN8Wqiq7UgwT5BQRU,23763
-nkululeko/models/model_xgb.py,sha256=ytBaSHZH8r7VvRYdmrBrQnzRM6V4HyCJ8O-v20J8G_g,448
+nkululeko/models/model_xgb.py,sha256=zfZM3lqH5uttVB18b1MRIhP9CCeCuIh1ycgOuFMcqUM,449
 nkululeko/models/model_xgr.py,sha256=H01FJCRgmX2unvambMs5TTCS9sI6VDB9ip9G6rVGt2c,419
+nkululeko/models/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nkululeko/models/tests/test_model_svm.py,sha256=spDlZmeBKBdK4EFBpOgEkaAfGeGH9kau6CqSWOY6Uag,1856
 nkululeko/reporting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/reporting/defines.py,sha256=0vh-Tlx4fAPpk1o6mP_4x3EkIoqzYMr38IZnj-JM5z4,641
 nkululeko/reporting/latex_writer.py,sha256=NGwSIfd4nfslDkNUOSZSdqY_VDLA8634thyhe-vj1bY,1824
 nkululeko/reporting/report.py,sha256=bYN8B66gg3IWHAyfd6uIVjpYKy3rOI6aEwgfXU0LSAY,1006
-nkululeko/reporting/report_item.py,sha256=AqKD40AlZpRuHLbggn5PkH6ctGJwh9rGNBNgOvgUODg,534
+nkululeko/reporting/report_item.py,sha256=drkknsyFhGviaPJNmPQtCXJmRhTSSfjNcJt0Bls6JAA,533
 nkululeko/reporting/reporter.py,sha256=-VyV0TZ0vBAx6UZNegnKS3i3WpkF27ntBRlYvp9NNiQ,20174
 nkululeko/reporting/result.py,sha256=G63a2tHCwHhM6NBJgYzsWKWJm4Yu3r4hsCHA2Km7eHU,1073
 nkululeko/segmenting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -112,10 +116,11 @@ nkululeko/segmenting/seg_silero.py,sha256=ulodnvtRq5MLHDxy_RmAK4tJg6h1d-mPq-uCPF
 nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=3Fyx8q8BSKYmiufT6OkRug9RATWmGrr9BaX_y8jziWo,3074
-nkululeko/utils/util.py,sha256=nZJtWqzFx3Zdp6Pve_ZAbb01yRTpIsgBXnoPy1VgtRE,17356
-nkululeko-0.94.1.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.94.1.dist-info/METADATA,sha256=JoeRpOcdclL11EV6vPNmw9gvmlm8VOO8yaoETjs2k-M,1169
-nkululeko-0.94.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-nkululeko-0.94.1.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.94.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.94.1.dist-info/RECORD,,
+nkululeko/utils/unzip.py,sha256=G68f5120TjwACZC3bQcneMniddnwubPbBdMc2L5KBOo,1206
+nkululeko/utils/util.py,sha256=6NDKhOx0fV5fKyhSoY4hem96p7OuPcmhCDQR9EzkQhw,17829
+nkululeko-0.94.3.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.94.3.dist-info/METADATA,sha256=QeZ9ZMTqwgdDvwRTCvgFO7X55_J84AWZh7jVf9uV-6M,2874
+nkululeko-0.94.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nkululeko-0.94.3.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.94.3.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
+nkululeko-0.94.3.dist-info/RECORD,,

{nkululeko-0.94.1.dist-info → nkululeko-0.94.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{nkululeko-0.94.1.dist-info → nkululeko-0.94.3.dist-info}/top_level.txt

@@ -1 +1,2 @@
+examples
 nkululeko

nkululeko-0.94.1.dist-info/METADATA

@@ -1,40 +0,0 @@
-Metadata-Version: 2.4
-Name: nkululeko
-Version: 0.94.1
-Summary: Machine learning audio prediction experiments based on templates
-Home-page: https://github.com/felixbur/nkululeko
-Author: Felix Burkhardt
-Author-email: fxburk@gmail.com
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Development Status :: 3 - Alpha
-Classifier: Topic :: Scientific/Engineering
-Requires-Python: >=3.9
-License-File: LICENSE
-Requires-Dist: audeer
-Requires-Dist: audformat
-Requires-Dist: audinterface
-Requires-Dist: audiofile
-Requires-Dist: audiomentations
-Requires-Dist: audmetric
-Requires-Dist: audonnx
-Requires-Dist: confidence_intervals
-Requires-Dist: datasets
-Requires-Dist: imageio
-Requires-Dist: matplotlib
-Requires-Dist: numpy
-Requires-Dist: opensmile
-Requires-Dist: pandas
-Requires-Dist: praat-parselmouth
-Requires-Dist: scikit_learn
-Requires-Dist: scipy
-Requires-Dist: seaborn
-Requires-Dist: sounddevice
-Requires-Dist: torch
-Requires-Dist: torchvision
-Requires-Dist: transformers
-Requires-Dist: umap-learn
-Requires-Dist: xgboost
-Requires-Dist: pylatex
-Dynamic: license-file