# A low ranked solution!!!😅

Summary: I used the "ai4bharat/indicwav2vec_v1_bengali" acoustic model and worked with the competition dataset. Since I don't have any physical GPU, I relied on Kaggle's free GPU. Training the model with the entire competition dataset was impossible for me, so I decided to focus on 29k validation samples that has more accurate labels and randomly selected an equal number of training samples. I still couldn't train with these 58k samples, so I further reduced it to 30k training samples by random selection and 2k validation samples. Before training, I normalized the labels also.
I experimented with various open-source acoustic models and found that "ai4bharat/indicwav2vec_v1_bengali" performed the best. I fine-tuned this model with my modified dataset in Kaggle. I saved checkpoints after 12 hours of training and then reload the checkpoint in another kernel and repeated this process three times (but you can't compare it with a continuous run, as the learning rate returns to its initial). Unfortunately, due to hardware limitations, I couldn't make further progress without a personal offline GPU workstation. That's why I gave up on the idea of using augmentations, incorporating a punctuation model, and so on.
I noticed that many sentences ended with "|" , so I added "|" at the end of all labels. But then I realized, generally bengali imperative sentences start with words like {'কি', 'কী', 'কেন', 'কিভাবে','কবে','কখন'}, so I used the "?" sign instead of "|" , after all the sentences which started with the words that indicate imperatives in Bengali. Additionally, I incorporated a 5-gram language model into my approach. So, that's it.