anwarvic / speaker-recognition Goto Github PK

File ".\ubm.py", line 202, in 
ubm.train()
File ".\ubm.py", line 50, in train
iterations=(1, 2, 2, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8)
File "C:\Users\jrodenas\Desktop\SpeakerRecognition\Speaker-Recognition\sidekit\mixture.py", line 672, in EM_split
self._init(features_server, feature_list, num_thread)
File "C:\Users\jrodenas\Desktop\SpeakerRecognition\Speaker-Recognition\sidekit\mixture.py", line 629, in _init
features = features_server.stack_features_parallel(feature_list, num_thread=num_thread)
File "C:\Users\jrodenas\Desktop\SpeakerRecognition\Speaker-Recognition\sidekit\features_server.py", line 666, in stack_features_parallel
return numpy.concatenate(output, axis=0)
ValueError: need at least one array to concatenate

import os
import sidekit
import numpy as np
import warnings
warnings.filterwarnings("ignore")
import logging
logging.basicConfig(level=logging.INFO)

from model_interface import SidekitModel



class UBM(SidekitModel):
    """Universal Background Model"""
    
    def __init__(self, conf_filepath):
        super().__init__(conf_filepath)
        # Number of Guassian Distributions
        self.NUM_GAUSSIANS = self.conf['num_gaussians']


    def train(self, SAVE=True):
        """
        This method is used to train our UBM model by doing the following:
        - Create FeatureServe for the enroll features
        - create use EM algorithm to train our UBM over the enroll features
        - create StatServer to save trained parameters
        - if Save arugment is True (which is by default), then it saves that
          StatServer.
        Args:
            SAVE (boolean): if True, then it will save the StatServer. If False,
               then the StatServer will be discarded.
        """
        #SEE: https://projets-lium.univ-lemans.fr/sidekit/tutorial/ubmTraining.html
        #D:\Merged_Arabic_Corpus_of_Isolated_Words\Allah\feat\enroll
        train_list = os.listdir(os.path.join(self.BASE_DIR, "feat", "enroll"))
        for i in range(len(train_list)):
            train_list[i] = train_list[i].split(".h5")[0]
        server = self.createFeatureServer("enroll")
        logging.info("Training...")
        ubm = sidekit.Mixture()
        # Set the model name
        ubm.name = "ubm_{}.h5".format(self.NUM_GAUSSIANS) 
        # Expectation-Maximization estimation of the Mixture parameters.
        ubm.EM_split(
            features_server=server, #sidekit.FeaturesServer used to load data
            feature_list=train_list, #list of feature files to train the model
            distrib_nb=self.NUM_GAUSSIANS, #number of Gaussian distributions
            num_thread=1, # number of parallel processes
            save_partial=True, # if False, it only saves the last model
            iterations=(1, 2)
            )
            # -> 2 iterations of EM with 2    distributions
            # -> 2 iterations of EM with 4    distributions
            # -> 4 iterations of EM with 8    distributions
            # -> 4 iterations of EM with 16   distributions
            # -> 4 iterations of EM with 32   distributions
            # -> 4 iterations of EM with 64   distributions
            # -> 8 iterations of EM with 128  distributions
            # -> 8 iterations of EM with 256  distributions
            # -> 8 iterations of EM with 512  distributions
            # -> 8 iterations of EM with 1024 distributions
        model_dir = os.path.join(self.BASE_DIR, "ubm")
        logging.info("Saving the model {} at {}".format(ubm.name, model_dir))
        ubm.write(os.path.join(model_dir, ubm.name))

        # Read idmap for the enrolling data
        enroll_idmap = sidekit.IdMap.read(os.path.join(self.BASE_DIR, "task", "enroll_idmap.h5"))
        # Create Statistic Server to store/process the enrollment data
        enroll_stat = sidekit.StatServer(statserver_file_name=enroll_idmap,
                                         ubm=ubm)
        logging.debug(enroll_stat)

        server.feature_filename_structure = os.path.join(self.BASE_DIR, "feat", "{}.h5")
        # Compute the sufficient statistics for a list of sessions whose indices are segIndices.
        #BUG: don't use self.NUM_THREADS when assgining num_thread as it's prune to race-conditioning
        enroll_stat.accumulate_stat(ubm=ubm,
                                    feature_server=server,
                                    seg_indices=range(enroll_stat.segset.shape[0])
                                   )
        if SAVE:
            # Save the status of the enroll data
            filename = "enroll_stat_{}.h5".format(self.NUM_GAUSSIANS)
            enroll_stat.write(os.path.join(self.BASE_DIR, "stat", filename))


if __name__ == "__main__":
    conf_filename = "conf.yaml"
    ubm = UBM(conf_filename)
    ubm.train()
#     ubm.evaluate()
#     ubm.plotDETcurve()
#     print( "Accuracy: {}%".format(ubm.getAccuracy()) )

Exception                                 Traceback (most recent call last)
<ipython-input-4-80b9baf34ccf> in <module>
    202     conf_filename = "conf.yaml"
    203     ubm = UBM(conf_filename)
--> 204     ubm.train()
    205 #     ubm.evaluate()
    206 #     ubm.plotDETcurve()

<ipython-input-4-80b9baf34ccf> in train(self, SAVE)
     77         enroll_stat.accumulate_stat(ubm=ubm,
     78                                     feature_server=server,
---> 79                                     seg_indices=range(enroll_stat.segset.shape[0])
     80                                    )
     81         if SAVE:

~\Anaconda3\lib\site-packages\sidekit\sidekit_wrappers.py in wrapper(*args, **kwargs)
    227         else:
    228             logging.debug("No Parallel processing with this module")
--> 229             func(*args, **kwargs)
    230 
    231     return wrapper

~\Anaconda3\lib\site-packages\sidekit\statserver.py in accumulate_stat(self, ubm, feature_server, seg_indices, channel_extension, num_thread)
    705             show = show[:show.rfind(channel_extension[channel])]
    706 
--> 707             cep, vad = feature_server.load(show, channel=channel)
    708             stop = vad.shape[0] if self.stop[idx] is None else min(self.stop[idx], vad.shape[0])
    709             logging.info('{} start: {} stop: {}'.format(show, self.start[idx], stop))

~\Anaconda3\lib\site-packages\sidekit\features_server.py in load(self, show, channel, input_feature_filename, label, start, stop)
    437                                                    input_feature_filename=feature_filename,
    438                                                    label=label,
--> 439                                                    start=start, stop=stop)
    440         else:
    441             logging.info('Extract tandem features from multiple sources')

~\Anaconda3\lib\site-packages\sidekit\features_server.py in get_features(self, show, channel, input_feature_filename, label, start, stop)
    482                                                                  label=label,
    483                                                                  start=start, stop=stop,
--> 484                                                                  global_cmvn=self.global_cmvn)
    485         # Post-process the features and return the features and vad label
    486         if global_cmvn:

~\Anaconda3\lib\site-packages\sidekit\frontend\io.py in read_hdf5_segment(file_handler, show, dataset_list, label, start, stop, global_cmvn)
    592 
    593     if show not in h5f:
--> 594         raise Exception('show {} is not in the HDF5 file'.format(show))
    595 
    596     # Get the selected segment

Exception: show enroll/S01.01.digits.wav is not in the HDF5 file

feat_dir = os.path.join(self.BASE_DIR, "feat")