audio_recognition | Audio fingerprinting and recognition in C | Speech library

This might be a bug in Bazel's repository rules. If you'd be so kind to file a bug, that'd be great!

As a workaround, extract the downloaded archive somewhere and replace the io_bazel_rules_closure rule in the WORKSPACE file with a local_repository rule pointing to the directory where you extracted the archive.

I posted this same question in the firebase quickstart iOS repository, And i got the following response DecodeWav op is never supported by TensorFlowLite. So at present Tensorflow Lite does not support audio processing even-though Tensorflow itself supports audio processing.

Have you synced the TensorFlow repository? The tutorial starts with "To begin the training process, go to the TensorFlow source tree" so the implied assumption is that you have in fact got the source.

If you have synced the repo it is in fact in there if you have not you will need to do this:

You can supply an input shape to the converter:

Let me try to answer your questions in turn.

1. If the graph def you build your model from is indeed frozen (i.e., all variables have been replaced by constants), there are no variables that need writing to the checkpoint that is commonly located at variables/variables*. So this looks explicable to me. -- That said, Hub modules would give you a way to avoid freezing graph defs: call the original graph building code in the module_fn, and restore pre-trained variables in the session before calling Module.export().

2. For your type of module, you get to make the rules. ;-) Hub Modules can accommodate all sorts of input and output shapes, including partially or fully unknown shapes. An input placeholder like above will have to have a shape that is compatible with the graph you are plugging it into. That graph, in turn, will use shapes that work with the convolutions it is doing. Generally speaking, it is often useful to use the leading dimension for batch size and leave that unspecified (None).

3. hub.get_expected_image_size() is meant for use with image inputs. I would avoid it here.

Its working, all i had to do was to run the command line in the TensorFlow source like this

After physically checking the detected words. I figured that accuracy is just 51%. It seems like lot of words were not detected may be because of the suppression period followed after the detection of the word or noise.