Luc

I had a similar problem and I fixed it by changing the method `concat_segs(times, segs)` to the following: ``` def concat_segs(times, segs): #Concatenate continuous voiced segments concat_seg = [] seg_concat...

@luckycallor Thanks for the quick answer. I'm trying to generate embeddings with the pre-trained network (ms1m-100) for later inference with nearest neighbour. I am asking because it seems like inference...

@Wxsang I currently use a margin of 5, so that could explain it. What margin have you found the most success with?

> Hi @lagidigu > > With Dopamine it is only possible to train using a single environment at a time. OpenAI Baselines on the other hand allows multiple environments concurrently...

@realbaker1967 I used the same decoder configuration as in the template file, as well as a the order 6 LM. Unfortunately, I cannot reproduce the reported WER of 3.97%. Its...

@realbaker1967 I get the same results after applying the template. This is strange. I will have to look into how the beam search decoder works exactly and will report back...

@realbaker1967 unfortunately I couldn't troubleshoot the issue. @gooofy do you know what might have changed with the decoder? The WER is a lot higher than 3.97%, unfortunately :/

@erksch did you have success training a streaming convnet on the mozilla dataset? I would be attempting something similar.