def _main(): """ Test model. """ from pyasv.data_manage import DataManage from pyasv import Config sys.path.append("../..") con = Config(name='MFM', n_speaker=100, batch_size=64, n_gpu=2, max_step=5, is_big_dataset=False, learning_rate=0.001, save_path='./save') x = np.random.random([6400, 50, 40, 1]) y = np.random.randint(0, 100, [6400, 1]) train = DataManage(x, y, con) enroll = train x = np.random.random([640, 50, 40, 1]) y = np.random.randint(0, 100, [640, 1]) validation = DataManage(x, y, con) test = validation run(con, train, validation) restore(con, enroll, test)
def _main(): """ Test model. """ from pyasv.data_manage import DataManage from pyasv import Config sys.path.append("../..") con = Config(name='ctdnn', n_speaker=100, batch_size=64 * 2, n_gpu=2, max_step=5, is_big_dataset=False, learning_rate=0.001, save_path='./save') #con.save('ctdnn') x = np.random.random([6500, 9, 40, 1]) y = np.random.randint(0, 99, [6500, 1]) enroll = DataManage(x, y, con) train = enroll x = np.random.random([1500, 9, 40, 1]) y = np.random.randint(0, 99, [1500, 1]) test = DataManage(x, y, con) validation = test run(con, train, validation, False) restore(con, enroll, test)
def _main(): """ Test model. """ from pyasv.data_manage import DataManage from pyasv import Config import sys sys.path.append("../..") print("Model test") print("input n_gpu", end="") a = int(eval(input())) con = Config(name='deepspeaker', n_speaker=100, batch_size=32 * max(1, a), n_gpu=a, max_step=5, is_big_dataset=False, learning_rate=0.001, save_path='./save', conv_weight_decay=0.01, fc_weight_decay=0.01, bn_epsilon=1e-3, deep_speaker_out_channel=[32, 64]) x = np.random.random([320, 100, 64, 1]) y = np.random.randint(0, 99, [320, 1]) train = DataManage(x, y, con) x = np.random.random([64, 100, 64, 1]) y = np.random.randint(0, 99, [64, 1]) validation = DataManage(x, y, con) # run(con, train, validation) restore(con, train, validation)
def _main(): """ Test model. """ """ Test model. """ from pyasv.data_manage import DataManage from pyasv import Config import sys sys.path.append("../..") print("Model test") print("input n_gpu", end="") a = int(eval(input())) con = Config(name='deepspeaker', n_speaker=100, batch_size=32*max(1, a), n_gpu=a, max_step=2, is_big_dataset=True, url_of_bigdataset_temp_file='./', learning_rate=0.001, save_path='./save', conv_weight_decay=0.01, fc_weight_decay=0.01, bn_epsilon=1e-3, deep_speaker_out_channel=[64, 128, 256, 512]) x = np.random.random([320, 100, 64, 1]) y = np.random.randint(0, 99, [320, 1]) train = DataManage4BigData(con, 'train') train.write_file(x, y) x = np.random.random([64, 100, 64, 1]) y = np.random.randint(0, 99, [64, 1]) validation = DataManage4BigData(con, 'validation') validation.write_file(x, y) run(con, train, validation) train.clear() validation.clear()
def _main(): """ Test model. """ from pyasv.data_manage import DataManage from pyasv import Config import sys sys.path.append("../..") con = Config(name='deepspeaker', n_speaker=100, batch_size=64, n_gpu=4, max_step=20, is_big_dataset=False, learning_rate=0.001, save_path='./save', conv_weight_decay=0.01, fc_weight_decay=0.01, bn_epsilon=1e-3) x = np.random.random([6400, 100, 64, 1]) y = np.random.randint(0, 100, [6400, 1]) train = DataManage(x, y, con) x = np.random.random([640, 100, 64, 1]) y = np.random.randint(0, 100, [640, 1]) validation = DataManage(x, y, con) run(con, train, validation)
import pyasv.speech_processing from pyasv.model import CTDnn from pyasv import Config root = "/opt/user1/fhq/asr/data-url/c863/" config = Config(config_path="./test.json") train_frames, train_labels = pyasv.speech_processing.ext_fbank_feature(root + 'train') enroll_frames, enroll_labels = pyasv.speech_processing.ext_fbank_feature( root + 'enroll') test_frames, test_labels = pyasv.speech_processing.ext_fbank_feature(root + 'test') m = CTDnn(config) m.run(train_frames, train_labels, enroll_frames, enroll_labels, test_frames, test_labels)
if i == j else tf.reduce_sum(mean_per_spkr[i, :] * embeddings[j, :, :], axis=1, keep_dims=True) for i in range(X) ], axis=1) for j in range(X) ], axis=0) # data shape is [spkr_num, utt_per_spkr, embedding_dim] # The shape of S is [spkr_num, utt_per_spkr, spkr_num] #S = ops.cosine(embeddings, mean_per_spkr, w=w, b=b) self.logger.debug(S.get_shape().as_list()) S_per_spkr = tf.reduce_sum(S, axis=-1) self.logger.debug(S_per_spkr.get_shape().as_list()) L = 2 * S - S_per_spkr self.logger.debug(L.get_shape().as_list()) return tf.reduce_sum(L) if __name__ == '__main__': x = tf.placeholder(dtpye=tf.float32, shape=[32, 150, 64]) config = Config('lstmp.yaml') model = LSTMP(config, 400, 3) out = model.inference(x) model.loss(out)