-
I am trying to use pre-trained model to transcribe my own audio files. but when I am doing that I am getting this error
"inconsistent tensor size, expected tensor [24 x 24] and src [30 x 30] to have…
-
in the command
"luajit ~/wav2letter/test.lua ~/librispeech-glu-highdropout.bin -progress -show -test dev-clean -save -datadir ~/librispeech-proc/ -dictdir ~/librispeech-proc/ -gfsai"
will the ken…
-
I am getting the following error when running test-one-file.lua:
~/usr/bin/luajit /wav2letter/test-one-file.lua /librispeech-glu-highdropout-cpu.bin /audio/test.wav -dict /librispeech-proc/letters.…
-
i am having am issue
I am using this command "luajit decode.lua librispeech-proc/ dev-other -show -letters librispeech-proc/letters-rep.lst -words dict.lst -lm 3-gram.pruned.3e-7.arpa -lmweight 3.16…
-
I'm trying to build kenlm for use with https://github.com/facebookresearch/wav2letter using the instructions in the readme but getting the following error and was hoping there is an easy fix.
```
…
-
I have tried to train wav2letter with 2-GPU (GTX 1080TI 11G) in a machine. In the case of a small dataset, hundreds audio files per GPU, MPI run well. However, I increases to thousands file per GPU, M…
-
Have you released the pytorch version of wav2letter
-
hi there
i have download pretrain mode and dev-set(openslr 12) and
test dev-clean and
try to decode... it has error
```
~/usr/bin/luajit ~/git/wav2letter/decode.lua ~/pretrain dev-clean …
-
Hello when I try to make rocks/beamer-scm-1.rockspec using the command
`cd beamer && KENLM_INC=$HOME/kenlm luarocks make rocks/beamer-scm-1.rockspec && cd ..`
I get this error:
> -- Using kenlm l…
-
when i transcribed my audio some how the repeated letters in a word is getting replaced by '1'.
example:
original:
two is a whole lot of our analytics around what customers are looking for based on…