facebook
/

xm_transformer_s2ut_hk-en

speech-to-speech-translation

Model card Files Files and versions Community

lpw commited on Oct 17, 2022

Commit

a3bfd4f

•

1 Parent(s): 1761e2f

Update README.md

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -16,10 +16,13 @@ datasets:
 ---
 ## xm_transformer_s2ut_hk-en
-Speech-to-speech translation model from fairseq:
 - Hokkien-English
-- Trained on MuST-C, TAT and Hokkien dramas
 - Speech synthesis with [facebook/unit_hifigan_mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj_dur](https://huggingface.co/facebook/unit_hifigan_mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj_dur)
 ## Usage
 ```python

 ---
 ## xm_transformer_s2ut_hk-en
+Speech-to-speech translation model with single-pass decoder (S2UT) from fairseq:
 - Hokkien-English
+- Trained with supervised data in TED, drama, TAT (https://sites.google.com/speech.ntut.edu.tw/fsw/home/tat-corpus) domain, and weakly supervised data in drama domain. See [here]
+(https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation)
+for training details.
 - Speech synthesis with [facebook/unit_hifigan_mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj_dur](https://huggingface.co/facebook/unit_hifigan_mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj_dur)
+- [Examples](https://github.com/facebookresearch/fairseq/tree/ust/examples/hokkien)
 ## Usage
 ```python