Support for BlockLSTM

Questions
1

I’m trying to convert Mozilla’s DeepSpeech model using tvmc but it throws an error:

Traceback (most recent call last):
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/__main__.py", line 24, in <module>
    tvmc.main.main()
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/main.py", line 94, in main
    sys.exit(_main(sys.argv[1:]))
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/main.py", line 87, in _main
    return args.func(args)
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/compiler.py", line 120, in drive_compile
    mod, params = frontends.load_model(args.FILE, args.model_format, args.input_shapes)
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/frontends.py", line 371, in load_model
    mod, params = frontend.load(path, shape_dict, **kwargs)
File "/home/user9886/Project/tvm/python/tvm/driver/tvmc/frontends.py", line 196, in load
    return relay.frontend.from_tensorflow(graph_def, shape=shape_dict, **kwargs)
File "/home/user9886/Project/tvm/python/tvm/relay/frontend/tensorflow.py", line 4077, in from_tensorflow
    mod, params = g.from_tensorflow(graph, layout, shape, outputs)
File "/home/user9886/Project/tvm/python/tvm/relay/frontend/tensorflow.py", line 3475, in from_tensorflow
    func = self._get_relay_func(graph, layout=layout, shape=shape, outputs=outputs)
File "/home/user9886/Project/tvm/python/tvm/relay/frontend/tensorflow.py", line 3302, in _get_relay_func
    "The following operators are not implemented: {}".format(missing_operators)
NotImplementedError: The following operators are not implemented: {'BlockLSTM', '`AudioSpectrogram`', 'Mfcc'}

as the error says, apparently, there is no support for these operations:

BlockLSTM
Mfcc
AudioSpectrogram

BTW, After taking a look at supported operations, I found out that LSTMBlockCell is supported but not BlockLSTM.

Is there any way for me to load this model?

If there is none, can you point out a doc to help me implement these operations?