Rafał Rolczyński

Hey @st-tomic My primary goal was slightly different. I just wanted to provide the good and open-sourced Polish ASR. I tried to experiment with the Mozilla DeepSpeech, Kaldi, etc. there...

Hey! Super weird. Could you provide more details?

Hey @HunbeomBak Alala... we have to fix it because the `multi_gpu_model` function is deprecated on 1 April, more details [here](https://www.tensorflow.org/api_docs/python/tf/keras/utils/multi_gpu_model). As you can see in this link, we have to...

It's quite a big change. As we can see, things tend to be more and more complicated when we try to stick with the "functional API". We wish to build...

hey @wahyubram82 I am super happy that you are here. Please could you provide more concrete questions? Please split it into mini problems - as small and abstract as possible....

It's now available the upgraded version 😊

It's now available the upgraded version 😊

It's now available the upgraded version 😊 (make sure that spacy is in the correct version)

hmm look at the `pipeline.predict` method that consumes the `input_batch` and easily you can modify a pipeline (or build your own) to do what you want 😊

Please read my blog post [here](https://rafalrolczynski.com/2021/03/07/aspect-based-sentiment-analysis/) maybe it'll give you more intuition how it works - this is an open-ended question 🤭 we take `w = x[0, text_mask]` the first...