-
Hi, can wav2letter train model for Mandarin?
wujsy updated
6 years ago
-
Hello!
I wonder if your recipe in librispeech is the one achieving WER published in paper? If so, can you tell the time it'll took the model to converge on 8 V100?
-
![image](https://user-images.githubusercontent.com/7293260/37180251-a9ef20ac-2328-11e8-97da-105ecbedbadb.png)
As you can see here I receive this error while trying to send audio, i use and LG G2 with…
Nhoya updated
6 years ago
-
https://github.com/facebookresearch/wav2letter/blob/153ac12304a51199249d797d365c25f13b5426ed/wav2letter/runtime/netutils.lua#L131
It should be :
`return nn.GatedLinearUnit(2):cuda()`
Otherwise…
-
(root) @gpucommtest1:~> luajit ~/wav2letter/train.lua --train -rundir ~/experiments -runname hello_librispeech -arch ~/wav2letter/arch/librispeech-glu-highdropout -lr 0.1 -lrcrit 0.0005 -pu 1 -linseg…
-
Dear Sir,
I am planning using the wav2letter for vietnamese. I have read the network architecture `arch/librispeech-glu-highdropout`, it has many layers. I would like to change the architecture.
…
-
I downloaded the pre-trained model and tried to run the decoder
`luajit ~/wav2letter/test.lua ~/librispeech-glu-highdropout.bin -progress -show -test dev-clean -save -datadir ~/librispeech-proc/ -dic…
srk97 updated
6 years ago
-
Hi, When I try to run
```
luajit /wav2letter/decode.lua models dev-clean -show -letters /librispeech-proc/letters-rep.lst -words /dict.lst -lm /3-gram.pruned.3e-7.arpa -lmweight 3.1639 -beamsize 2…
-
In the README, under subsection **"Running the decoder (inference)"**, the wget command should have a newline before luajit.
Currently it reads as follows:
wget http://www.openslr.org/resources…
-
Hi,
I used logits from another model (Wav2Letter) to test the CTC decoder, however, I can't get correct results from the decoder, for example,
I got :"sometimemesttheeultbotthfehinatetwhorkhasreal…