nkululeko 0.86.0__py3-none-any.whl → 0.86.1__py3-none-any.whl

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.86.0"
+VERSION="0.86.1"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -72,8 +72,9 @@ class Experiment:
         if self.util.config_val("REPORT", "latex", False):
             self.report.export_latex()
 
-    def get_name(self):
-        return self.util.get_exp_name()
+    # moved to util
+    # def get_name(self):
+    #     return self.util.get_exp_name()
 
     def set_globals(self, config_obj):
         """install a config object in the global space"""

nkululeko/models/model_tuned.py

@@ -64,7 +64,8 @@ class TunedModel(BaseModel):
 
     def _init_model(self):
         model_path = "facebook/wav2vec2-large-robust-ft-swbd-300h"
-        pretrained_model = self.util.config_val("MODEL", "pretrained_model", model_path)
+        pretrained_model = self.util.config_val(
+            "MODEL", "pretrained_model", model_path)
         self.num_layers = None
         self.sampling_rate = 16000
         self.max_duration_sec = 8.0
@@ -95,6 +96,7 @@ class TunedModel(BaseModel):
 
         # load pre-trained model
         if self.is_classifier:
+            self.util.debug(f"Task is classification.")
             le = glob_conf.label_encoder
             mapping = dict(zip(le.classes_, range(len(le.classes_))))
             target_mapping = {k: int(v) for k, v in mapping.items()}
@@ -102,15 +104,16 @@ class TunedModel(BaseModel):
                 value: key for key, value in target_mapping.items()
             }
             self.config = transformers.AutoConfig.from_pretrained(
-                model_path,
+                pretrained_model,
                 num_labels=len(target_mapping),
                 label2id=target_mapping,
                 id2label=target_mapping_reverse,
                 finetuning_task=target_name,
             )
         else:
+            self.util.debug(f"Task is regression.")
             self.config = transformers.AutoConfig.from_pretrained(
-                model_path,
+                pretrained_model,
                 num_labels=1,
                 finetuning_task=target_name,
             )
@@ -253,6 +256,9 @@ class TunedModel(BaseModel):
         else:
             criterion = ConcordanceCorCoeff()
 
+        # set push_to_hub value, default false
+        push = self.util.config_val("MODEL", "push_to_hub", False)
+
         class Trainer(transformers.Trainer):
             def compute_loss(
                 self,
@@ -299,6 +305,8 @@ class TunedModel(BaseModel):
             load_best_model_at_end=True,
             remove_unused_columns=False,
             report_to="none",
+            push_to_hub=push,
+            hub_model_id=f"{self.util.get_name()}",
         )
 
         trainer = Trainer(

nkululeko/resample.py

@@ -11,22 +11,32 @@ from nkululeko.utils.util import Util
 
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
+from nkululeko.utils.files import find_files
 
 
 def main(src_dir):
     parser = argparse.ArgumentParser(
-        description="Call the nkululeko RESAMPLE framework.")
+        description="Call the nkululeko RESAMPLE framework."
+    )
     parser.add_argument("--config", default=None,
                         help="The base configuration")
     parser.add_argument("--file", default=None,
                         help="The input audio file to resample")
-    parser.add_argument("--replace", action="store_true",
-                        help="Replace the original audio file")
+    parser.add_argument(
+        "--folder",
+        default=None,
+        help="The input directory containing audio files and subdirectories to resample",
+    )
+    parser.add_argument(
+        "--replace", action="store_true", help="Replace the original audio file"
+    )
 
     args = parser.parse_args()
 
-    if args.file is None and args.config is None:
-        print("ERROR: Either --file or --config argument must be provided.")
+    if args.file is None and args.folder is None and args.config is None:
+        print(
+            "ERROR: Either --file, --folder, or --config argument must be provided."
+        )
         exit()
 
     if args.file is not None:
@@ -42,6 +52,20 @@ def main(src_dir):
         util.debug(f"Resampling audio file: {args.file}")
         rs = Resampler(df_sample, not_testing=True, replace=args.replace)
         rs.resample()
+    elif args.folder is not None:
+        # Load all audio files in the directory and its subdirectories into a DataFrame
+        files = find_files(args.folder, relative=True, ext=["wav"])
+        files = pd.Series(files)
+        df_sample = pd.DataFrame(index=files)
+        df_sample.index = audformat.utils.to_segmented_index(
+            df_sample.index, allow_nat=False
+        )
+
+        # Resample the audio files
+        util = Util("resampler", has_config=False)
+        util.debug(f"Resampling audio files in directory: {args.folder}")
+        rs = Resampler(df_sample, not_testing=True, replace=args.replace)
+        rs.resample()
     else:
         # Existing code for handling INI file
         config_file = args.config
@@ -66,6 +90,7 @@ def main(src_dir):
 
         if util.config_val("EXP", "no_warnings", False):
             import warnings
+
             warnings.filterwarnings("ignore")
 
         # Load the data
@@ -74,7 +99,8 @@ def main(src_dir):
         # Split into train and test
         expr.fill_train_and_tests()
         util.debug(
-            f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
+            f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}"
+        )
 
         sample_selection = util.config_val(
             "RESAMPLE", "sample_selection", "all")

nkululeko/utils/util.py

@@ -134,6 +134,12 @@ class Util:
             pd_series.dtype, pd.CategoricalDtype
         )
 
+    def get_name(self):
+        """
+        Get the name of the experiment
+        """
+        return self.config["EXP"]["name"]
+
     def get_exp_dir(self):
         """
         Get the experiment directory

{nkululeko-0.86.0.dist-info → nkululeko-0.86.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nkululeko
-Version: 0.86.0
+Version: 0.86.1
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt
@@ -256,6 +256,7 @@ There's my [blog](http://blog.syntheticspeech.de/?s=nkululeko) with tutorials:
 * [Compare several databases](http://blog.syntheticspeech.de/2024/01/02/nkululeko-compare-several-databases/)
 * [Tweak the target variable for database comparison](http://blog.syntheticspeech.de/2024/03/13/nkululeko-how-to-tweak-the-target-variable-for-database-comparison/)
 * [How to run multiple experiments in one go](http://blog.syntheticspeech.de/2022/03/28/how-to-run-multiple-experiments-in-one-go-with-nkululeko/)
+* [How to finetune a transformer-model](http://blog.syntheticspeech.de/2024/05/29/nkululeko-how-to-finetune-a-transformer-model/)
 
 ### <a name="helloworld">Hello World example</a>
 * NEW: [Here's a Google colab that runs this example out-of-the-box](https://colab.research.google.com/drive/1GYNBd5cdZQ1QC3Jm58qoeMaJg3UuPhjw?usp=sharing#scrollTo=4G_SjuF9xeQf), and here is the same [with Kaggle](https://www.kaggle.com/felixburk/nkululeko-hello-world-example)
@@ -333,6 +334,11 @@ F. Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben and Björn Schulle
 Changelog
 =========
 
+Version 0.86.1
+--------------
+* functionality to push to hub
+* fixed bug that prevented wavlm finetuning
+
 Version 0.86.0
 --------------
 * added regression to finetuning

{nkululeko-0.86.0.dist-info → nkululeko-0.86.1.dist-info}/RECORD

@@ -2,11 +2,11 @@ nkululeko/__init__.py,sha256=62f8HiEzJ8rG2QlTFJXUCMpvuH3fKI33DoJSj33mscc,63
 nkululeko/aug_train.py,sha256=YhuZnS_WVWnun9G-M6g5n6rbRxoVREz6Zh7k6qprFNQ,3194
 nkululeko/augment.py,sha256=4MG0apTAG5RgkuJrYEjGgDdbodZWi_HweSPNI1JJ5QA,3051
 nkululeko/cacheddataset.py,sha256=lIJ6hUo5LoxSrzXtWV8mzwO7wRtUETWnOQ4ws2XfL1E,969
-nkululeko/constants.py,sha256=hvi1X27m7vcqkB_Rgl7alourAusZB1mjPxdW4ChdVyU,39
+nkululeko/constants.py,sha256=pZ3DZYgXdEpxfaj-mnI6q21TyYMa2QQG_sKa6CBxCCA,39
 nkululeko/demo.py,sha256=8bl15Kitoesnz8oa8yrs52T6YCSOhWbbq9PnZ8Hj6D0,3232
 nkululeko/demo_feats.py,sha256=sAeGFojhEj9WEDFtG3SzPBmyYJWLF2rkbpp65m8Ujo4,2025
 nkululeko/demo_predictor.py,sha256=es56xbT8ifkS_vnrlb5NTZT54gNmeUtNlA4zVA_gnN8,4757
-nkululeko/experiment.py,sha256=gUJsBMWuadqxEVzuPVToQzFHC9FRUadptP49kTcBiGs,30962
+nkululeko/experiment.py,sha256=24FmvF9_zNXE86fO6gzss1M-BjceOCiV6nyJAs0SM_Y,30986
 nkululeko/explore.py,sha256=lDzRoW_Taa5u4BBABZLD89BcQWnYlrftJR4jgt1yyj0,2609
 nkululeko/export.py,sha256=mHeEAAmtZuxdyebLlbSzPrHSi9OMgJHbk35d3DTxRBc,4632
 nkululeko/feature_extractor.py,sha256=8mssYKmo4LclVI-hiLmJEDZ0ZPyDavFG2YwtXcrGzwM,3976
@@ -19,7 +19,7 @@ nkululeko/nkuluflag.py,sha256=PGWSmZz-PiiHLgcZJAoGOI_Y-sZDVI1ksB8p5r7riWM,3725
 nkululeko/nkululeko.py,sha256=Kn3s2E3yyH8cJ7z6lkMxrnqtCxTu7-qfe9Zr_ONTD5g,1968
 nkululeko/plots.py,sha256=nd9tF_61DyAx7oGZF8gTrHXazkgFjFe4eClxu1nQ_XU,23276
 nkululeko/predict.py,sha256=sF091sSSLnEWcISx9ZcULLie3tY5XeFsQJd6b3vrxFg,2409
-nkululeko/resample.py,sha256=IPtYqU0nhZ-CqO_O1jJN0EvpfjxHZdFRwdTpEJOVuaQ,3354
+nkululeko/resample.py,sha256=2d9eao_0sLrGZ_KSl8OVKsPor3BkFrlmMhrpB9WelIs,4267
 nkululeko/runmanager.py,sha256=eTM1DNQKt1lxYhzt4vZyZluPXW9sWlIJHNQzex4lkJU,7624
 nkululeko/scaler.py,sha256=4nkIqoajkIkuTPK0Z02ifMN_awl6fP_i-GBYdoGYgGM,4101
 nkululeko/segment.py,sha256=YLKckX44tbvTb3LrdgYw9X4guzuF27sutl92z9DkpZU,4835
@@ -88,7 +88,7 @@ nkululeko/models/model_svm.py,sha256=rsME3KvKvNG7bdE5lbvYUu85WZhaASZxxmdNDIVJRZ4
 nkululeko/models/model_svr.py,sha256=_YZeksqB3eBENGlg3g9RwYFlk9rQQ-XCeNBKLlGGVoE,725
 nkululeko/models/model_tree.py,sha256=rf16faUm4o2LJgkoYpeY998b8DQIvXZ73_m1IS3TnnE,417
 nkululeko/models/model_tree_reg.py,sha256=IgQcPTE-304HQLYSKPF8Z4ot_Ur9dH01fZjS0nXke_M,428
-nkululeko/models/model_tuned.py,sha256=J5CemIAW_WhZIQgppFgPChrsMJvGYzJlCvJC8O62l9M,18049
+nkululeko/models/model_tuned.py,sha256=eiSKFmObn9_VNTqF1lZvWbyyWxvhy1PVjOiIcs3YiGA,18379
 nkululeko/models/model_xgb.py,sha256=Thgx5ESdIok4v72mKh4plxpo4smGcKALWNCJTDScY0M,447
 nkululeko/models/model_xgr.py,sha256=aGBtNGLWjOE_2rICGYGFxmT8DtnHYsIl1lIpMtghHsY,418
 nkululeko/reporting/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -104,9 +104,9 @@ nkululeko/segmenting/seg_silero.py,sha256=lLytS38KzARS17omwv8VBw-zz60RVSXGSvZ5Ev
 nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=UiGAtZRWYjHSvlmPaTMtzyNNGE6qaLaxQkybctS7iRM,4021
 nkululeko/utils/stats.py,sha256=1yUq0FTOyqkU8TwUocJRYdJaqMU5SlOBBRUun9STo2M,2829
-nkululeko/utils/util.py,sha256=b1IHFucRNuF9Iyv5IJeK4AEg0Rga0xKG80UM5GWWdHA,13816
-nkululeko-0.86.0.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.86.0.dist-info/METADATA,sha256=KrHrjQ6rc4oGxN4EJ_TuZ0dVGGI-qIxw8dY1RBTCnLo,36852
-nkululeko-0.86.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nkululeko-0.86.0.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
-nkululeko-0.86.0.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=mK1MgO14NinrPhavJw72eR_2WN_kBKjVKiEJnzvdO1Q,13946
+nkululeko-0.86.1.dist-info/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.86.1.dist-info/METADATA,sha256=LXoMlzo5QBzABv0fpIDvf4nYDjCJkRCZL1XmffikrRc,37088
+nkululeko-0.86.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+nkululeko-0.86.1.dist-info/top_level.txt,sha256=DPFNNSHPjUeVKj44dVANAjuVGRCC3MusJ08lc2a8xFA,10
+nkululeko-0.86.1.dist-info/RECORD,,