Commits

History for

Commits on May 2, 2021

'sentenciepiece' -> 'sentencepiece'
jim-hays-root
committed
7d06911
'Dictionnary which map' -> 'Dictionary which maps'
jim-hays-root
committed
3c1bbc4
'Cotaining' -> 'Containing'
jim-hays-root
committed
e669fe7
'Japenese' -> 'Japanese'
jim-hays-root
committed
f9ab6cf
'Setence' -> 'Sentence'
jim-hays-root
committed
ed1b88b
'Japanse' -> 'Japanese'
jim-hays-root
committed
0d4dfde

Commits on Feb 19, 2021

add tokenizer in templates + small fix in SE part
mirco
committed
efe3c7f
fixed tests
mirco
committed
f4cfebd
ASR template (first part) + support json in tokenizer
mirco
committed
0a88cee

Commits on Feb 14, 2021

updating tokenizers/SentencePiece.py
nauman-daw
committed
2f6aa59

Commits on Jan 29, 2021

normalise all utils
TParcollet
committed
5859b2d

Commits on Jan 20, 2021

fixed typos in docstrings
mirco
committed
5be94bb

Commits on Jan 19, 2021

Dataio without underscore
Gastron
committed
e15547d

Commits on Jan 15, 2021

Update init.py to work as a pip package
pplantinga
committed
d277af4

Commits on Jan 11, 2021

Commits on Jan 8, 2021

last fixes
mravanelli
committed
d949691

Commits on Jan 7, 2021

add Tokenizer recipe
aheba
committed
1d5e3f3
add user_defined_symbols to spbrain tokenizer
aheba
committed
41fa814
add tokenizer coverage checking on train/dev/test subset
aheba
committed
1722c8b

Commits on Dec 11, 2020

add main_process checking and ddp_barrier
aheba
committed
6b456de

Commits on Nov 24, 2020

fix formatting
lugoschl
committed
066f6b6

Commits on Nov 10, 2020

First commit with SLU recipe
lugoschl
committed
7c80614

Commits on Oct 15, 2020

remove minloglevel from documentation
Abdelwahab Heba
committed
125184b
remove minloglevel and use sentencepiece v0.1.91
Abdelwahab Heba
committed
63ccab7
Fix sentencepiece minloglevel issue - close #328
Abdelwahab Heba
committed
be03dfb

Commits on Sep 15, 2020

Update error rate stats to include prediction lengths, SentencePiece, and decoder paths
pplantinga
committed
b23675b

Commits on Aug 16, 2020

fix error in _csv2text()
jjery2243542
committed
389d82c
fix doc-test
jjery2243542
committed
b1534e9
add char_format_input option for large vocab case
jjery2243542
committed
7ddd494

Commits on Aug 5, 2020

add minloglevel for avoiding logging from sentencepiece lib
Abdelwahab Heba
committed
89baa35

Commits on Jul 30, 2020

added convolution frontend and support for mixed presision
jianyuan.zhong
committed
cdc10a6

Commits on Jul 27, 2020

Merge remote-tracking branch 'origin/BPE_tokenizer' into transformer-clean-bpe
jianyuan.zhong
committed
fde218a
some changes
jianyuan.zhong
committed
12920f3