Murtuza Dahodwala

I am trying to build a character based seq2seq model using tensorflow for food item names correction. The input/output would be like > IN: Cheessseee Quisadillas > OUT: Cheese Quesadillas...

How can i use GPT to correct the alignment and spellings in a sentence?

1

I have a dataset with 20lakh food item names. And another clean dataset with all the correct vocabularies. I want to use GPT to build a item name corrector. For...

Hello, I have files which are corpora of categories. Each corpus for each category. now I want to classify a new text into one of these categories. Can you please...

I have a dataset of food item names and I want to train xfspell on my dataset. My doubt is how do I create .tok file? I do not see...

Loading private model from huggingface hub

2

I have created a basic flow which connects the LLMChain with huggingface hub and a basic prompt. The flow works fine with any public open source models like falcon-7b. However,...

Hello, Can you please tell me how can i use language model for sequence alignment and spell correction like in the speech recognition system? https://github.com/joydeb28/NLP-Notebooks/blob/8f67ef5d90e459facde62a4c556cd99261756670/1.1-language-model/language_model_keras.ipynb

HI, Is there any way where we can encode the words which are out of vocabulary and find out the best possible prediction without giving a KeyError? https://github.com/joydeb28/NLP-Notebooks/blob/master/1.4-machine-translation/seq2seq.ipynb

Ngrams

4

Does this model takes care of ngrams like "hot dog" = "hotdog", "ice cream" = "icecream"?? I have these ngrams in my training data Also what if i want to...

Cannot run example code.

4

I cannot run the example code that is provided in the markdown. I have tried running it with GPU in local and CPU and GPU both in colab. While trying...