-
I submitted a 4-node task with 1GPU for each node.
But it exit with exception.
Some of the log information is as follows:
NCCL WARN Connect to 10.38.10.112 failed : Connection refused
The strange…
-
``` shell
Pretraining
Wed Apr 8 12:05:13 2020[0]:INFO:absl:
Wed Apr 8 12:05:13 2020[0]:================================= Parse Parameter ==============================
Wed Apr 8 12:05:13 2020[0…
-
Hi, I just find when use Parallel_WaveGAN to synthesize, the spectrum will be not contin…
-
When training the model, how to set copy_from in tr_dset?
-
Follow the instruction here:
https://github.com/athena-team/athena/blob/master/deploy/README.md
Step 4. Compiling the C++ Codes and Running the executable file, run make command, it throw exceptio…
fming updated
4 years ago
-
I have a trained e2e ASR transducer model that trained on fbank features (Librispeech). I'm trying to concatenate auxiliary vector to the fbank input during testing. The idea is to feed the model cont…
-
Hello everyone!
I am using one of the ASR egs. When I try to decide which beam-size, ctc-weight and lm-weight should I use, but while repeating inference with the same parameters, results are diffe…
vcjob updated
4 years ago
-
I am trying recognize speech.
Job fails. Getting this:
`steps/make_fbank_pitch.sh: [info]: no segments file exists: assuming wav.scp indexed by utterance.`
`run.pl: job failed, log is in decode/…
-
Hi,
I'm having import issues when I run (only some) recipes through Docker. After checking that the docker/build tests were fine and training a few different ASR models without trouble, I tried ljs…
-
I followed the instructions in the README and was able to run an experiment with the configuration located at `cfg/TIMIT_baselines/TIMIT_LSTM_fmllr_cudnn.cfg`. However, instead of obtaining the report…