python demo_cli.py --low_mem
Arguments:
    enc_model_fpath:   encoder/saved_models/pretrained.pt
    syn_model_dir:     synthesizer/saved_models/logs-pretrained
    voc_model_fpath:   vocoder/saved_models/pretrained/pretrained.pt
    low_mem:           True
    no_sound:          False

Running a test of your configuration...

Found 1 GPUs available. Using GPU 0 (GeForce MX150) of compute capability 6.1 with 2.1Gb total memory.

Preparing the encoder, the synthesizer and the vocoder...
Loaded encoder "pretrained.pt" trained to step 1564501
Found synthesizer "pretrained" trained to step 278000
Building Wave-RNN
Trainable Parameters: 4.481M
Loading model weights at vocoder/saved_models/pretrained/pretrained.pt
Testing your configuration with small inputs.
	Testing the encoder...
	Testing the synthesizer... (loading the model will output a lot of text)
WARNING: Logging before flag parsing goes to stderr.
W0710 12:56:14.965464 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:91: The name tf.nn.rnn_cell.RNNCell is deprecated. Please use tf.compat.v1.nn.rnn_cell.RNNCell instead.

W0710 12:56:14.969801 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/tacotron2.py:13: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.

Constructing model: Tacotron
W0710 12:56:14.969986 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/tacotron2.py:16: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

W0710 12:56:14.974001 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/tacotron2.py:22: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

W0710 12:56:14.980313 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/tacotron.py:86: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
    options available in V2.
    - tf.py_function takes a python function which manipulates tf eager
    tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
    an ndarray (just call tensor.numpy()) but having access to eager tensors
    means `tf.py_function`s can use accelerators such as GPUs as well as
    being differentiable using a gradient tape.
    - tf.numpy_function maintains the semantics of the deprecated tf.py_func
    (it is not differentiable, and manipulates numpy arrays). It drops the
    stateful argument making all functions stateful.

W0710 12:56:14.985866 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/tacotron.py:123: The name tf.train.replica_device_setter is deprecated. Please use tf.compat.v1.train.replica_device_setter instead.

W0710 12:56:14.986169 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/tacotron.py:135: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

W0710 12:56:14.986651 140347480831744 deprecation.py:506] From Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0710 12:56:14.995551 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:112: LSTMCell.__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
W0710 12:56:14.996792 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:421: conv1d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.keras.layers.Conv1D` instead.
W0710 12:56:15.090229 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:422: batch_normalization (from tensorflow.python.layers.normalization) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.BatchNormalization instead.  In particular, `tf.control_dependencies(tf.GraphKeys.UPDATE_OPS)` should not be used (consult the `tf.keras.layers.batch_normalization` documentation).
W0710 12:56:15.146689 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:425: dropout (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dropout instead.
W0710 12:56:15.252574 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:236: bidirectional_dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.Bidirectional(keras.layers.RNN(cell))`, which is equivalent to this API
W0710 12:56:15.252838 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py:464: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.RNN(cell)`, which is equivalent to this API
W0710 12:56:15.324985 140347480831744 deprecation.py:506] From Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py:961: calling Zeros.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0710 12:56:15.755512 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:156: The name tf.nn.rnn_cell.LSTMStateTuple is deprecated. Please use tf.compat.v1.nn.rnn_cell.LSTMStateTuple instead.

W0710 12:56:15.755714 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py:244: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0710 12:56:16.229463 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/attention.py:158: The name tf.layers.Conv1D is deprecated. Please use tf.compat.v1.layers.Conv1D instead.

W0710 12:56:16.229856 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/attention.py:161: The name tf.layers.Dense is deprecated. Please use tf.compat.v1.layers.Dense instead.

W0710 12:56:16.230358 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:305: MultiRNNCell.__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0.
W0710 12:56:16.340025 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/synthesizer/models/modules.py:269: dense (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dense instead.
W0710 12:56:16.568230 140347480831744 ag_logging.py:145] Entity <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52c390ba8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: converting <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52c390ba8>>: ValueError: Failed to parse source code of <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52c390ba8>>, which Python reported as:
    def __call__(self, inputs, state, scope=None):
        """Runs vanilla LSTM Cell and applies zoneout.
        """
        # Apply vanilla LSTM
        output, new_state = self._cell(inputs, state, scope)

        if self.state_is_tuple:
            (prev_c, prev_h) = state
            (new_c, new_h) = new_state
        else:
            num_proj = self._cell._num_units if self._cell._num_proj is None else \
				self._cell._num_proj
            prev_c = tf.slice(state, [0, 0], [-1, self._cell._num_units])
            prev_h = tf.slice(state, [0, self._cell._num_units], [-1, num_proj])
            new_c = tf.slice(new_state, [0, 0], [-1, self._cell._num_units])
            new_h = tf.slice(new_state, [0, self._cell._num_units], [-1, num_proj])

        # Apply zoneout
        if self.is_training:
            # nn.dropout takes keep_prob (probability to keep activations) not drop_prob (
			# probability to mask activations)!
            c = (1 - self._zoneout_cell) * tf.nn.dropout(new_c - prev_c,
                                                         (1 - self._zoneout_cell)) + prev_c
            h = (1 - self._zoneout_outputs) * tf.nn.dropout(new_h - prev_h,
                                                            (1 - self._zoneout_outputs)) + prev_h

        else:
            c = (1 - self._zoneout_cell) * new_c + self._zoneout_cell * prev_c
            h = (1 - self._zoneout_outputs) * new_h + self._zoneout_outputs * prev_h

        new_state = tf.nn.rnn_cell.LSTMStateTuple(c, h) if self.state_is_tuple else tf.concat(1, [c,
                                                                                                  h])

        return output, new_state

This may be caused by multiline strings or comments not indented at the same level as the code.
W0710 12:56:16.605508 140347480831744 ag_logging.py:145] Entity <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52bfc8198>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: converting <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52bfc8198>>: ValueError: Failed to parse source code of <bound method ZoneoutLSTMCell.__call__ of <synthesizer.models.modules.ZoneoutLSTMCell object at 0x7fa52bfc8198>>, which Python reported as:
    def __call__(self, inputs, state, scope=None):
        """Runs vanilla LSTM Cell and applies zoneout.
        """
        # Apply vanilla LSTM
        output, new_state = self._cell(inputs, state, scope)

        if self.state_is_tuple:
            (prev_c, prev_h) = state
            (new_c, new_h) = new_state
        else:
            num_proj = self._cell._num_units if self._cell._num_proj is None else \
				self._cell._num_proj
            prev_c = tf.slice(state, [0, 0], [-1, self._cell._num_units])
            prev_h = tf.slice(state, [0, self._cell._num_units], [-1, num_proj])
            new_c = tf.slice(new_state, [0, 0], [-1, self._cell._num_units])
            new_h = tf.slice(new_state, [0, self._cell._num_units], [-1, num_proj])

        # Apply zoneout
        if self.is_training:
            # nn.dropout takes keep_prob (probability to keep activations) not drop_prob (
			# probability to mask activations)!
            c = (1 - self._zoneout_cell) * tf.nn.dropout(new_c - prev_c,
                                                         (1 - self._zoneout_cell)) + prev_c
            h = (1 - self._zoneout_outputs) * tf.nn.dropout(new_h - prev_h,
                                                            (1 - self._zoneout_outputs)) + prev_h

        else:
            c = (1 - self._zoneout_cell) * new_c + self._zoneout_cell * prev_c
            h = (1 - self._zoneout_outputs) * new_h + self._zoneout_outputs * prev_h

        new_state = tf.nn.rnn_cell.LSTMStateTuple(c, h) if self.state_is_tuple else tf.concat(1, [c,
                                                                                                  h])

        return output, new_state

This may be caused by multiline strings or comments not indented at the same level as the code.
initialisation done /gpu:0
W0710 12:56:16.995547 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/models/tacotron.py:286: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

Initialized Tacotron model. Dimensions (? = dynamic shape):
  Train mode:               False
  Eval mode:                False
  GTA mode:                 False
  Synthesis mode:           True
  Input:                    (?, ?)
  device:                   0
  embedding:                (?, ?, 512)
  enc conv out:             (?, ?, 512)
  encoder out (cond):       (?, ?, 768)
  decoder out:              (?, ?, 80)
  residual out:             (?, ?, 512)
  projected residual out:   (?, ?, 80)
  mel out:                  (?, ?, 80)
  <stop_token> out:         (?, ?)
  Tacotron Parameters       28.439 Million.
Loading checkpoint: synthesizer/saved_models/logs-pretrained/taco_pretrained/tacotron_model.ckpt-278000
W0710 12:56:17.326570 140347480831744 deprecation_wrapper.py:119] From Real-Time-Voice-Cloning/synthesizer/tacotron2.py:63: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

W0710 12:56:17.471510 140347480831744 deprecation.py:323] From Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
E0710 12:56:19.739237 140347480831744 driver.py:321] Call to cuInit results in CUDA_ERROR_NOT_INITIALIZED
multiprocess.pool.RemoteTraceback:
"""
Traceback (most recent call last):
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 230, in initialize
    self.cuInit(0)
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 293, in safe_cuda_api_call
    self._check_error(fname, retcode)
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 328, in _check_error
    raise CudaAPIError(retcode, msg)
numba.cuda.cudadrv.driver.CudaAPIError: [3] Call to cuInit results in CUDA_ERROR_NOT_INITIALIZED

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/multiprocess/pool.py", line 119, in worker
    result = (True, func(*args, **kwds))
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/multiprocess/pool.py", line 47, in starmapstar
    return list(itertools.starmap(args[0], args[1]))
  File "Real-Time-Voice-Cloning/synthesizer/inference.py", line 111, in _one_shot_synthesize_spectrograms
    numba.cuda.select_device(0)
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/api.py", line 302, in select_device
    context = devices.get_context(device_id)
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/devices.py", line 194, in get_context
    return _runtime.get_or_create_context(devnum)
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/devices.py", line 162, in get_or_create_context
    return self.push_context(self.gpus[devnum])
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/devices.py", line 40, in __getitem__
    return self.lst[devnum]
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/devices.py", line 26, in __getattr__
    numdev = driver.get_device_count()
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 339, in get_device_count
    self.cuDeviceGetCount(byref(count))
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 273, in __getattr__
    self.initialize()
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/numba/cuda/cudadrv/driver.py", line 233, in initialize
    raise CudaSupportError("Error at driver init: \n%s:" % e)
numba.cuda.cudadrv.error.CudaSupportError: Error at driver init:
[3] Call to cuInit results in CUDA_ERROR_NOT_INITIALIZED:
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "demo_cli.py", line 90, in <module>
    mels = synthesizer.synthesize_spectrograms(texts, embeds)
  File "Real-Time-Voice-Cloning/synthesizer/inference.py", line 94, in synthesize_spectrograms
    [(self.checkpoint_fpath, embeddings, texts)])[0]
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/multiprocess/pool.py", line 274, in starmap
    return self._map_async(func, iterable, starmapstar, chunksize).get()
  File "Real-Time-Voice-Cloning/env/lib/python3.6/site-packages/multiprocess/pool.py", line 644, in get
    raise self._value
numba.cuda.cudadrv.error.CudaSupportError: Error at driver init:
[3] Call to cuInit results in CUDA_ERROR_NOT_INITIALIZED: