Barry Haddow

I have the same problem. This is happening in AudioDictionary.dummy_sentence() where (I think) the code is creating a dummy audio segment, and trying to initialise it with `uniform_(self.nspecial + 1,...

Training is progressing and it is creating checkpoint models. The log just seems to be full of warnings though. Should I see validation scores? I am using pytorch 1.4 too.

I found the validation scores. Doe this look normal? ``` | epoch 001 | valid on 'valid' subset | valid_loss 278.29 | valid_nll_loss 1.80495 | valid_ppl 3.49 | num_updates 1884...

I'm using the training command suggested here https://towardsdatascience.com/getting-started-with-end-to-end-speech-translation-3634c35a6561

Thanks @mattiadg , I will look into it. Although I suspect I did something wrong in preprocessing, since it works OK for @Chaitanya-git without pre-training. Note that I am training...

I am seeing the same issue with the translations. The output of the en-es system is nearly always one word (gracias). We will try the asr pretraining, but welcome any...

I was using a single GPU. If I increase update-freq, will that give me the equivalent effect to using more GPUs? (if slower). I could also increase the batch size,...

I checked the output of my first run, and it's gracias all the way down. I am running again (without pretraining) using 2 GPUs and doubling the update-freq to 32....

I estimated the average batch size by dividing the number of sentences by the number of updates per epoch.

Hi I see the same error. Making the change ``` +++ b/fairseq/models/speech_to_text/xm_transformer.py @@ -643,7 +643,7 @@ class XMTransformerModel(FairseqEncoderDecoderModel): base_architecture(args) if getattr(args, "load_pretrained_decoder_from", None) is not None: ckpt = torch.load(getattr(args, "load_pretrained_decoder_from",...