Zipformer-DictinctK: Differentiating Repeated Characters

[yfyeung]

Keeping a separate vector as an nn.Parameter in the model, and adding it times k/(1+k) to the embedding before the ReLU during training and decoding.

It only supports greedy_search and greedy_search_batch.

[rouseabout]

Will this model change help with the kind of problem raised in issue https://github.com/k2-fsa/icefall/issues/1356 ? Thanks.