to-schi/asr-deepspeech2-tensorflow

An end-to-end speech recognition engine similar to DeepSpeech2

Hi there 👋

I'm a data scientist with a background in political science and project management. I like repairing things and solving problems with data and code.

Languages and tools I use:

Contact me on:

Support my work:

asr-deepspeech2-tensorflow's Issues

InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 2

Hello Sir,

i got error while i am build your code in our dataset.
i followed all step and every thing work fine except here

`for batch in train_dataset.take(10):
print(batch)
label_tokens = batch[1][1]

print(label_tokens)
label = tf.strings.reduce_join(num_to_char(label_tokens)).numpy().decode("utf-8")
print(label)`

i got this error

`---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
in ()
----> 1 for batch,x,y in train_dataset.take(10):
2 print(batch)
3 label_tokens = batch[1][1]
4
5 print(label_tokens)

3 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name)
7162 def raise_from_not_ok_status(e, name):
7163 e.message += (" name: " + name if name is not None else "")
-> 7164 raise core._status_to_exception(e) from None # pylint: disable=protected-access
7165
7166

InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 2
[[{{node Squeeze}}]] [Op:IteratorGetNext]`