Hugging Face's logo

johntsi
/
ZeroSwot-Medium_asr-cv_mt-covost2_en-to-15

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
baaafcb
•
1 Parent(s): 71d04fe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -54,8 +54,7 @@ The compression module is a light-weight transformer that takes as input the hid
54
 
55
  ## Version
56
 
57
- This version of ZeroSwot is trained with ASR data from CommonVoice, and adapted [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the [nllb-200-distilled-600M_covost2](https://huggingface.co/johntsi/nllb-200-distilled-600M_covost2_en-to-15), which is a finetuned NLLB on CoVoST2 text data.
58
-
59
  We have more versions available:
60
 
61
  | Models | ASR data | NLLB version |
 
54
 
55
  ## Version
56
 
57
+ This version of ZeroSwot is trained with ASR data from CommonVoice. It adapts [wav2vec2.0-large](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) to the embedding space of the [nllb-200-distilled-600M_covost2](https://huggingface.co/johntsi/nllb-200-distilled-600M_covost2_en-to-15) model, which is a multilingually finetuned NLLB on MuST-C MT data.
 
58
  We have more versions available:
59
 
60
  | Models | ASR data | NLLB version |