AlonSh

I'm having the same issue. The original module has many more layers and weights than the generated module. @Zheweiqiu did you find a solution?

@cydawn I found a pytorch implementation, rewrote the model in keras and found a tool that loads pytorch params into tf graphs. I'm sorry but that work was done in...

> Any news on that ? @AlonSh maybe a PR if you made the change on your side ? I think I've just kept using it that way, but I...

Hey @janscas , I think certificate based auth is an awesome way to help rid the world of wandering API keys and increase the trust of using this library. I...

I think that I'm also experiencing the same memory leak on add_word. Would love to see any updates :) Edit - I was experiencing a different memory leak. My leak...

Yeah: create some automaton create a multiprocessing Pool and do: ``` pool.apply_async( run_automaton, (automaton, text), callback=callback_success, error_callback=_my_error_callback, ) ``` and you'll see your memory exploding after some calls.