# 92th Place Solution

Thank you Bengali.AI & Kaggle for organizing this competition.
Overview of the Approach
ASR Model
Dataset: I only use small subset of competition dataset with filter audios which duration is less then 1 sec. as outlier. Removing all kinds of punctuation. Removing all kinds of punctuation then Normalization
Augmentation: BackgroundNoise, Gain
Pretrain model: arijitx-full-model/wav2vec2-xls-r-300m-bengali
I don't have the time or resources to train more epochs (the model only train on 1 epoch). If possible the results could be even better!
Language Model
Same as public notebook: 5-gram LM (arijitx-full-model/wav2vec2-xls-r-300m-bengali)