Speech Recognition
Crow
Text conversion command
for file in `ls ../Inuit-Yupik/ess/monolingual_corpus/sivuqam_nangaghnegha/sivuqam_volume2/volume...
Deep speech build
These instructions are for those of us who wish to have a version of Mozilla's DeepSpeech where t...
Deep Speech decoder breakdown
Generate trie
This issues a call to scorer::setup()?
Deep Speech Scorer Refactor
I have successfully renamed all variables dealing with the scorer and reran everything. The next...
Potentially using tensorflow api in python instead of c++
the tensorflow api in c++ is a bear to use. no one really uses it much and it has some noteworthy...
Building mozilla with deepspeech integration
https://treeherder.mozilla.org/#/jobs?repo=try&revision=5266680e9e43df3dd2a922b334ce9b33df73a...
Datasets
Guarani BABEL is stored at /nas/data/lorelei/ldc_downloads/LDC2016E19__IARPA_Babel_Guarani_Langua...
Guarani
Using pytorch deepspeech
Data stats
Conversational training: 37.55 hours find wav/ | xargs -I {} -r soxi -D {} | awk '{sum += $1} E...
Conversion of sph files
(metalearn) (base) kenneth@mwanafunzi:/home/data/corpora/speech/IARPA-babel305b-v1.0c-build$ find...
New Page
Early stuff I was doing was seeing the first epochs perform the best and high sensitivity to numb...