mattiadg / FBK-Fairseq-ST

An adaptation of Fairseq to (End-to-end) speech translation.

mattiadg/FBK-Fairseq-ST Issues

Training with custom dataset
Updated 3 years ago
Error when not using any distance penalty
Updated 3 years ago2
download the MuST-C corpus
Closed 4 years ago
ValueError: Cannot load file containing pickled data when allow_pickle=False
Closed 4 years ago
Generate translation on a single audio
Closed 4 years ago4
RuntimeError: CUDA out of memory after training 1 epoch
Updated 4 years ago10
IndexError while recreating the MustC experiment(tgt_sizes is has a shape (0,)
Closed 4 years ago2
train.py, FileNotFoundError, asking for dict.source.txt
Closed 4 years ago1
Speech Translation on a custom dataset
Closed 4 years ago16
Command to reproduce results on MuST-C failing
Updated 4 years ago43
Readme preprocessing command
Closed 4 years ago1
preprocess.py ValueError: Cannot register model architecture for unknown model type (r_transformer_lm)
Closed 4 years ago3
ConvAttention2D
Closed 4 years ago1