1/* Copyright 2017 The TensorFlow Authors. All Rights Reserved.
2
3Licensed under the Apache License, Version 2.0 (the "License");
4you may not use this file except in compliance with the License.
5You may obtain a copy of the License at
6
7 http://www.apache.org/licenses/LICENSE-2.0
8
9Unless required by applicable law or agreed to in writing, software
10distributed under the License is distributed on an "AS IS" BASIS,
11WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12See the License for the specific language governing permissions and
13limitations under the License.
14==============================================================================*/
15
16// See docs in ../ops/audio_ops.cc
17
18#include "tensorflow/core/framework/bounds_check.h"
19#include "tensorflow/core/framework/op_kernel.h"
20#include "tensorflow/core/framework/register_types.h"
21#include "tensorflow/core/framework/tensor.h"
22#include "tensorflow/core/framework/tensor_shape.h"
23#include "tensorflow/core/framework/types.h"
24#include "tensorflow/core/lib/core/status.h"
25#include "tensorflow/core/lib/wav/wav_io.h"
26
27namespace tensorflow {
28
29// Encode a tensor as audio samples into the contents of a WAV format file.
30class EncodeWavOp : public OpKernel {
31 public:
32 explicit EncodeWavOp(OpKernelConstruction* context) : OpKernel(context) {}
33
34 void Compute(OpKernelContext* context) override {
35 const Tensor& audio = context->input(0);
36 OP_REQUIRES(context, audio.dims() == 2,
37 errors::InvalidArgument("audio must be 2-dimensional",
38 audio.shape().DebugString()));
39 const Tensor& sample_rate_tensor = context->input(1);
40 OP_REQUIRES(context, TensorShapeUtils::IsScalar(sample_rate_tensor.shape()),
41 errors::InvalidArgument(
42 "Input sample_rate should be a scalar tensor, got ",
43 sample_rate_tensor.shape().DebugString(), " instead."));
44 const int32_t sample_rate = sample_rate_tensor.scalar<int32>()();
45 OP_REQUIRES(
46 context,
47 FastBoundsCheck(audio.NumElements(), std::numeric_limits<int32>::max()),
48 errors::InvalidArgument(
49 "Cannot encode audio with >= max int32 elements"));
50
51 const int32_t channel_count = static_cast<int32>(audio.dim_size(1));
52 const int32_t sample_count = static_cast<int32>(audio.dim_size(0));
53
54 // Encode audio to wav string.
55 Tensor* output = nullptr;
56 OP_REQUIRES_OK(context,
57 context->allocate_output(0, TensorShape({}), &output));
58 OP_REQUIRES_OK(context,
59 wav::EncodeAudioAsS16LEWav(
60 audio.flat<float>().data(), sample_rate, channel_count,
61 sample_count, &output->scalar<tstring>()()));
62 }
63};
64REGISTER_KERNEL_BUILDER(Name("EncodeWav").Device(DEVICE_CPU), EncodeWavOp);
65
66} // namespace tensorflow
67