Hugging Face's logo

johntsi
/
ZeroSwot-Medium_asr-mustc_mt-mustc_en-to-8

Automatic Speech Recognition
Transformers
Safetensors
zero_swot_encoder
feature-extraction
zeroswot
speech translation
zero-shot
end-to-end
nllb
wav2vec2
custom_code
Model card Files Community
johntsi commited on
Commit
d3569bf
·
verified ·
1 Parent(s): 9e618f4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -76,7 +76,7 @@ The compression module is a light-weight transformer that takes as input the hid
76
 
77
  ## Version
78
 
79
- This version of ZeroSwot is trained with ASR data from MuST-C v1.0. It adapts [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the embedding space of [nllb-200-distilled-600M_mustc](https://huggingface.co/johntsi/nllb-200-distilled-600M_mustc_en-to-8), which is a finetuned NLLB on MuST-C MT data.
80
 
81
  We have more versions available:
82
 
 
76
 
77
  ## Version
78
 
79
+ This version of ZeroSwot is trained with ASR data from MuST-C v1.0. It adapts [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the embedding space of the [nllb-200-distilled-600M_mustc](https://huggingface.co/johntsi/nllb-200-distilled-600M_mustc_en-to-8) model, which is a multilingually finetuned NLLB on MuST-C MT data.
80
 
81
  We have more versions available:
82