How to use a Keras LSTM with batch size of 1 ? (avoid zero padding)

Question

I want to train a Keras LSTM using a batch size of one. In this case I wouldn't need zero padding so far I understood. The necessity for zero padding comes from equalizing the size of the batches, right?

It turns out this is not as easy as I thought.

My network looks like this:

model = Sequential()
model.add(Embedding(output_dim=embeddings.shape[1],
input_dim=embeddings.shape[0],
                     weights=[embeddings],
                     trainable=False))
model.add(Dropout(0.2))
model.add(Bidirectional(LSTM(100,
           return_sequences=True,
           activation="tanh",kernel_initializer="glorot_uniform")))
model.add(TimeDistributed(Dense(maxLabel)))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
          optimizer='sgd',
          metrics=['accuracy'])

model.fit(x_train, y_train, epochs=20, batch_size=1, shuffle=True)

I naively provide my training data and training labels as simple numpy array with this shape properties: X: (2161,) Y: (2161,)

I get now a ValueError: Error when checking target: expected activation_1 to have 3 dimensions, but got array with shape (2161, 1)

I am not sure how to satisfy this 3-D property without zero-padding which is what I want to avoid when working with batch sizes of one anyway.

Does anyone see what I am doing wrong?