Time Series Transformer (trained on monash_tsf/tourism-monthly)

Time Series Transformer model trained on the tourism-monthly dataset for 30 epochs.

Model description

The Time Series Transformer is a vanilla encoder-decoder Transformer for time-series forecasting. The model is trained in the same way as one trains a Transformer for machine translation. At inference time, the model autoregressively generates samples, one time step at a time.

Usage

We refer to the documentation regarding usage.

Downloads last month
1,943
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Dataset used to train huggingface/time-series-transformer-tourism-monthly