Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
facebook
/
textless_sm_it_fr
like
1
Audio-to-Audio
Fairseq
audio
speech-to-speech-translation
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Community
1
Use this model
f94f3de
textless_sm_it_fr
/
config_multitask.yaml
gmdnn
Update config_multitask.yaml
f94f3de
over 1 year ago
raw
Copy download link
history
blame
No virus
132 Bytes
source_unit:
data:
N/A
decoder_type:
transformer
dict:
dict_800.txt
encoder_layer:
6
loss_weight:
8.0
target_type:
text