# 126th Place Solution

[This solution](https://www.kaggle.com/code/markwijkhuizen/aslfr-inference-python3-7-tpu)
is an improved version of
[my public notebook](https://www.kaggle.com/code/markwijkhuizen/aslfr-transformer-training-inference)
with the following modifications:
Running on a TPU to allow for faster training and experimentation
Increased number of input frames 128 → 288
Batch size 64 → 512
Units encoder 384 → 288
Units decoder 256 → 128
For an in depth explanation of the approach I refer to the public notebook code and comment section.
The expect the performance boost in my private notebook is mostly due to the decreased model capacity and increased batch size, this should reduce overfitting.