Open nikifori opened 2 weeks ago
Thanks Konstantinos for reporting this and sorry for the trouble. We talked via email, so here a summary:
tssep
, I have to wait for MERL to merge the code (https://github.com/merlresearch/tssep/pull/1)aux_feature_statistics_domain_adaptation
has a large impact on the WER. (6%
-> >70%
). So it is not recommented to do that.nn_segmenter
parameters in the config to use less frames. Since the eval minibatch size is 1, it cannot be reduced.
Hi,
While trying to run the evaluation on the pretrained model: https://github.com/fgnt/tssep_data/blob/master/egs/libri_css/README.md#steps-to-evaluate-a-pretrained-model
I got this error on the
make tssep_pretrained_eval
command:I have not changed anything into the config files neither on
tssep_pretrained_77_62000.yaml
which is the base. However, I thinksimLibriCSS_oracle_ivectors.json
is unecessary for evaluation, since for the evaluation only the produced i-vectors are needed (libriCSS_espnet_ivectors.json
), and for domain adaptation feature_statistics.pkl is downloaded successfully.Update (4/9/2024)
just a quick update.
I managed to overcome the previous error by commenting out the following lines in the config.yaml:
and by changing:
The problem now is that I receive CUDA_OUT_OF_MEMORY error:
But there is not any argument about eval batch size or anything relevant to tweak. Have you got any thoughts on that?
Thanks