nkululeko 0.95.8__tar.gz → 0.96.0__tar.gz

{nkululeko-0.95.8 → nkululeko-0.96.0}/CHANGELOG.md

@@ -1,6 +1,14 @@
 Changelog
 =========
 
+Version 0.96.0 (25-07-14)
+--------------------------
+* added Bert feature extractor
+
+Version 0.95.9 (25-07-14)
+--------------------------
+* added google translation
+
 Version 0.95.8 (25-07-14)
 --------------------------
 * fix bug that bool was not detected as categorical

{nkululeko-0.95.8/nkululeko.egg-info → nkululeko-0.96.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.8
+Version: 0.96.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

nkululeko-0.96.0/nkululeko/autopredict/ap_translate.py

@@ -0,0 +1,39 @@
+"""A translator for text.
+
+Currently based on google translate.
+"""
+
+from nkululeko.utils.util import Util
+
+
+class TextTranslator:
+    """Translator.
+
+    translate text with the google translate model
+    """
+
+    def __init__(self, df, util=None):
+        self.df = df
+        if util is not None:
+            self.util = util
+        else:
+            # create a new util instance
+            # this is needed to access the config and other utilities
+            # in the autopredict module
+            self.util = Util("translator")
+            
+        self.language = self.util.config_val("PREDICT", "target_language", "en")
+        from nkululeko.autopredict.google_translator import GoogleTranslator
+        self.translator = GoogleTranslator(
+            language=self.language,
+            util=self.util,
+        )
+
+    def predict(self, split_selection):
+        self.util.debug(f"translating text for {split_selection} samples")
+        df = self.translator.translate_index(
+            self.df
+        )
+        return_df = self.df.copy()
+        return_df[self.language] = df[self.language].values
+        return return_df

nkululeko-0.96.0/nkululeko/autopredict/google_translator.py

@@ -0,0 +1,63 @@
+import os
+
+import pandas as pd
+import torch
+from tqdm import tqdm
+
+import asyncio
+from googletrans import Translator
+
+import audeer
+import audiofile
+
+from nkululeko.utils.util import Util
+
+import httpx
+
+class GoogleTranslator:
+    def __init__(self, language="en", util=None):
+        self.language = language
+        self.util = util
+
+    async def translate_text(self, text):
+        async with Translator() as translator:
+            result = translator.translate(text, dest="en")
+            return (await result).text
+
+    def translate_index(self, df:pd.DataFrame) ->  pd.DataFrame:
+        """Transcribe the audio files in the given index.
+
+        :param index: Index containing tuples of (file, start, end).
+        :return: DataFrame with transcriptions indexed by the original index.
+        :rtype: pd.DataFrame
+        """
+        file_name = ""
+        seg_index = 0
+        translations = []
+        translator_cache = audeer.mkdir(
+            audeer.path(self.util.get_path("cache"), "translations"))
+        file_name = ""
+        for idx, row in tqdm(df.iterrows(), total=len(df)):
+            file = idx[0]
+            start = idx[1]
+            end = idx[2]
+            if file != file_name:
+                file_name = file
+                seg_index = 0
+            cache_name = audeer.basename_wo_ext(file)+str(seg_index)
+            cache_path = audeer.path(translator_cache, cache_name + ".json")
+            if os.path.isfile(cache_path):
+                translation = self.util.read_json(cache_path)["translation"]
+            else:
+                text = row['text']
+                translation = asyncio.run(self.translate_text(text))
+                self.util.save_json(cache_path, 
+                                {"translation": translation, 
+                                 "file": file, 
+                                 "start": start.total_seconds(), 
+                                 "end": end.total_seconds()})
+            translations.append(translation)
+            seg_index += 1
+
+        df = pd.DataFrame({self.language:translations}, index=df.index)
+        return df

{nkululeko-0.95.8 → nkululeko-0.96.0}/nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.95.8"
+VERSION="0.96.0"
 SAMPLING_RATE = 16000

{nkululeko-0.95.8 → nkululeko-0.96.0}/nkululeko/experiment.py

@@ -574,6 +574,11 @@ class Experiment:
 
                 predictor = TextPredictor(df, self.util)
                 df = predictor.predict(sample_selection)
+            elif target == "translation":
+                from nkululeko.autopredict.ap_translate import TextTranslator
+
+                predictor = TextTranslator(df, self.util)
+                df = predictor.predict(sample_selection)
             elif target == "arousal":
                 from nkululeko.autopredict.ap_arousal import ArousalPredictor
 

nkululeko-0.96.0/nkululeko/feat_extract/feats_bert.py

@@ -0,0 +1,105 @@
+import os
+
+import pandas as pd
+from tqdm import tqdm
+import transformers
+import torch 
+from transformers import BertTokenizer, BertModel
+
+from nkululeko.feat_extract.featureset import Featureset
+import nkululeko.glob_conf as glob_conf
+
+
+class Bert(Featureset):
+    """Class to extract bert embeddings"""
+
+    def __init__(self, name, data_df, feat_type):
+        """Constructor.
+
+        If_train is needed to distinguish from test/dev sets,
+        because they use the codebook from the training
+        """
+        super().__init__(name, data_df, feat_type)
+        cuda = "cuda" if torch.cuda.is_available() else "cpu"
+        self.device = self.util.config_val("MODEL", "device", cuda)
+        self.model_initialized = False
+        if feat_type == "bert":
+            self.feat_type = "bert-base-uncased"
+        else:
+            self.feat_type = feat_type
+
+    def init_model(self):
+        # load model
+        self.util.debug(f"loading {self.feat_type} model...")
+        model_path = self.util.config_val(
+            "FEATS", "bert.model", f"google-bert/{self.feat_type}"
+        )
+        config = transformers.AutoConfig.from_pretrained(model_path)
+        layer_num = config.num_hidden_layers
+        hidden_layer = int(self.util.config_val("FEATS", "bert.layer", "0"))
+        config.num_hidden_layers = layer_num - hidden_layer
+        self.util.debug(f"using hidden layer #{config.num_hidden_layers}")
+
+        self.tokenizer = BertTokenizer.from_pretrained(model_path)
+        self.model = BertModel.from_pretrained(model_path, config=config).to(
+            self.device
+        )
+        print(f"initialized {self.feat_type} model on {self.device}")
+        self.model.eval()
+        self.model_initialized = True
+
+    def extract(self):
+        """Extract the features or load them from disk if present."""
+        store = self.util.get_path("store")
+        storage = os.path.join(store, f"{self.name}.pkl")
+        extract = self.util.config_val("FEATS", "needs_feature_extraction", False)
+        no_reuse = eval(self.util.config_val("FEATS", "no_reuse", "False"))
+        if extract or no_reuse or not os.path.isfile(storage):
+            if not self.model_initialized:
+                self.init_model()
+            self.util.debug(
+                f"extracting {self.feat_type} embeddings, this might take a while..."
+            )
+            emb_series = pd.Series(index=self.data_df.index, dtype=object)
+            for idx, row in tqdm(self.data_df.iterrows(), total=len(self.data_df)):
+                file = idx[0]
+                text = row['text']
+                emb = self.get_embeddings(text, file)
+                emb_series[idx] = emb
+            # print(f"emb_series shape: {emb_series.shape}")
+            self.df = pd.DataFrame(emb_series.values.tolist(), index=self.data_df.index)
+            # print(f"df shape: {self.df.shape}")
+            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():
+                self.util.error(
+                    f"got nan: {self.df.shape} {self.df.isnull().sum().sum()}"
+                )
+
+    def get_embeddings(self, text, file):
+        r"""Extract embeddings from raw audio signal."""
+        try:
+            with torch.no_grad():
+                inputs = self.tokenizer(text, return_tensors="pt")
+                outputs = self.model(**inputs)
+                # mean pooling 
+                y = torch.mean(outputs[0], dim=1)
+                y = y.ravel()
+        except RuntimeError as re:
+            print(str(re))
+            self.util.error(f"couldn't extract file: {file}")
+            y = None
+        if y is None:
+            return None
+        return y.detach().cpu().numpy()
+
+    def extract_sample(self, text):
+        self.init_model()
+        feats = self.get_embeddings(text, "no file")
+        return feats

{nkululeko-0.95.8 → nkululeko-0.96.0}/nkululeko/feature_extractor.py

@@ -80,7 +80,7 @@ class FeatureExtractor:
             return MLD_set
 
         elif feats_type.startswith(
-            ("wav2vec2", "hubert", "wavlm", "spkrec", "whisper", "ast", "emotion2vec")
+            ("bert", "wav2vec2", "hubert", "wavlm", "spkrec", "whisper", "ast", "emotion2vec")
         ):
             return self._get_feat_extractor_by_prefix(feats_type)
 

{nkululeko-0.95.8 → nkululeko-0.96.0/nkululeko.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.8
+Version: 0.96.0
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.95.8 → nkululeko-0.96.0}/nkululeko.egg-info/SOURCES.txt

@@ -108,8 +108,10 @@ nkululeko/autopredict/ap_sid.py
 nkululeko/autopredict/ap_snr.py
 nkululeko/autopredict/ap_stoi.py
 nkululeko/autopredict/ap_text.py
+nkululeko/autopredict/ap_translate.py
 nkululeko/autopredict/ap_valence.py
 nkululeko/autopredict/estimate_snr.py
+nkululeko/autopredict/google_translator.py
 nkululeko/autopredict/whisper_transcriber.py
 nkululeko/autopredict/tests/__init__.py
 nkululeko/autopredict/tests/test_whisper_transcriber.py
@@ -123,6 +125,7 @@ nkululeko/feat_extract/feats_analyser.py
 nkululeko/feat_extract/feats_ast.py
 nkululeko/feat_extract/feats_auddim.py
 nkululeko/feat_extract/feats_audmodel.py
+nkululeko/feat_extract/feats_bert.py
 nkululeko/feat_extract/feats_clap.py
 nkululeko/feat_extract/feats_emotion2vec.py
 nkululeko/feat_extract/feats_hubert.py

{nkululeko-0.95.8 → nkululeko-0.96.0}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nkululeko"
-version = "0.95.8"
+version = "0.96.0"
 description = "Machine learning audio prediction experiments based on templates"
 authors = [
     {name = "Felix Burkhardt", email = "fxburk@gmail.com"},