Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
1
xls-r-300m-sv-robust / run_speech_recognition_ctc.py

Commit History

clean code. add logs. log audio correctly
fbda210

marinone94 commited on

restructure main code
8829a08

marinone94 commited on

fix print len eval
ace0e10

marinone94 commited on

fix bug in split
9a45fab

marinone94 commited on

Training in progress, step 20
a90a966

marinone94 commited on

split training in two, one per dataset
0a1c33d

marinone94 commited on

fix training script
4e5c598

marinone94 commited on

train only on nst
09dc80f

marinone94 commited on

log df of train and test data
044dff6

marinone94 commited on

shuffle dataset- fix ttraining params.
38706e1

marinone94 commited on

new training
ba980b2

marinone94 commited on

fix column removal issue
bf11fb8

marinone94 commited on

columns as args in common cols
57ad2fb

marinone94 commited on

ifx var error
dceb34d

marinone94 commited on

remove columns not in common across datasets
1d35cf4

marinone94 commited on

do not remove columns when building vocab
575922b

marinone94 commited on

correct filtering column
393fd68

marinone94 commited on

fix replace in batch
9be1ce7

marinone94 commited on

fix typo in skipping dataset
f267bb5

marinone94 commited on

add decoding to get correct swedish chars
cd904f4

marinone94 commited on

remove punkt och komma
71e9ea9

marinone94 commited on

fix oom vocab building. adjust run params
c6104eb

marinone94 commited on

allow for multiple datasets from hf in run
79a4bc0

marinone94 commited on

add eda, clean script
c9cb648

marinone94 commited on

remove add lm from script
060c28e

marinone94 commited on

Add LM in training script
c369c05

marinone94 commited on

Training in progress, step 5
b99a621

marinone94 commited on