search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.8k stars 810 forks source link

Reproducing colab inference script on local doesn't work #734

Closed kamil-bentounes closed 2 years ago

kamil-bentounes commented 2 years ago

Hello,

Im trying to run the french TTS model on my computer:

Here is all error log:

2022-01-11 14:48:09.344053: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.348924: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.349254: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.349706: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-01-11 14:48:09.350095: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.350414: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.350728: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.779283: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.779667: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.779946: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-01-11 14:48:09.780202: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 3616 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 2060, pci bus id: 0000:01:00.0, compute capability: 7.5
Traceback (most recent call last):
  File "test.py", line 16, in <module>
    tacotron2 = TFAutoModel.from_pretrained("tensorspeech/tts-tacotron2-synpaflex-fr", name="tacotron2")
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow_tts/inference/auto_model.py", line 104, in from_pretrained
    model._build()
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow_tts/inference/savable_models.py", line 43, in _build
    self([input_ids, input_lengths, speaker_ids])
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/engine/base_layer.py", line 1037, in __call__
    outputs = call_fn(inputs, *args, **kwargs)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow_tts/inference/savable_models.py", line 37, in call
    return super().inference(input_ids, input_lengths, speaker_ids)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 885, in __call__
    result = self._call(*args, **kwds)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 933, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 759, in _initialize
    self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3066, in _get_concrete_function_internal_garbage_collected
    graph_function, _ = self._maybe_define_function(args, kwargs)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3463, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3298, in _create_graph_function
    func_graph_module.func_graph_from_py_func(
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1007, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py", line 668, in wrapped_fn
    out = weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py", line 3990, in bound_method_wrapper
    return wrapped_fn(*args, **kwargs)
  File "/home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 994, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow_tts/models/tacotron2.py:904 inference  *
        encoder_hidden_states = self.encoder(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow_tts/models/tacotron2.py:252 call  *
        outputs = self.bilstm(conv_outputs, mask=input_mask)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/wrappers.py:583 __call__  **
        return super(Bidirectional, self).__call__(inputs, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/engine/base_layer.py:1037 __call__
        outputs = call_fn(inputs, *args, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/wrappers.py:698 call
        y = self.forward_layer(forward_inputs,
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/recurrent.py:659 __call__
        return super(RNN, self).__call__(inputs, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/engine/base_layer.py:1037 __call__
        outputs = call_fn(inputs, *args, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/recurrent_v2.py:1253 call
        runtime) = lstm_with_backend_selection(**normal_lstm_kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/recurrent_v2.py:1648 lstm_with_backend_selection
        last_output, outputs, new_h, new_c, runtime = defun_standard_lstm(**params)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3038 __call__
        filtered_flat_args) = self._maybe_define_function(args, kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3463 _maybe_define_function
        graph_function = self._create_graph_function(args, kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3298 _create_graph_function
        func_graph_module.func_graph_from_py_func(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:1007 func_graph_from_py_func
        func_outputs = python_func(*func_args, **func_kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/recurrent_v2.py:1379 standard_lstm
        last_output, outputs, new_states = backend.rnn(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206 wrapper
        return target(*args, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/backend.py:4354 rnn
        output_time_zero, _ = step_function(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/layers/recurrent_v2.py:1367 step
        z = backend.bias_add(z, bias)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206 wrapper
        return target(*args, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/keras/backend.py:5975 bias_add
        return tf.nn.bias_add(x, bias, data_format='NCHW')
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206 wrapper
        return target(*args, **kwargs)
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/ops/nn_ops.py:3496 bias_add
        return gen_nn_ops.bias_add(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/ops/gen_nn_ops.py:690 bias_add
        _, _, _op, _outputs = _op_def_library._apply_op_helper(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/op_def_library.py:748 _apply_op_helper
        op = g._create_op_internal(op_type_name, inputs, dtypes=None,
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:599 _create_op_internal
        return super(FuncGraph, self)._create_op_internal(  # pylint: disable=protected-access
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:3561 _create_op_internal
        ret = Operation(
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:2041 __init__
        self._c_op = _create_c_op(self._graph, node_def, inputs,
    /home/kamil/TTS/test-venv/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:1883 _create_c_op
        raise ValueError(str(e))

    ValueError: Shape must be at least rank 3 but is rank 2 for '{{node BiasAdd}} = BiasAdd[T=DT_FLOAT, data_format="NCHW"](add, bias)' with input shapes: [?,1024], [1024].

Can you please help me ?

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.