Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
facebook
/
textless_sm_it_es
like
0
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
07e4138
textless_sm_it_es
/
config_multitask.yaml
cndn
programmatically upload /textless_it\_es
07e4138
almost 2 years ago
raw
Copy download link
history
blame
No virus
128 Bytes
source_unit:
data:
N/A
decoder_type:
transformer
dict:
dict.txt
encoder_layer:
6
loss_weight:
8.0
target_type:
text