johntsi commited on
Commit
5b0d62b
1 Parent(s): 5c6605a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -251,7 +251,7 @@ tags:
251
 
252
  ZeroSwot is a state-of-the-art zero-shot end-to-end Speech Translation system.
253
 
254
- <div align=center><img src="resources/intro.png" height="75%" width="75%"/></div>
255
 
256
  The model is created by adapting a wav2vec2.0-based encoder to the embedding space of NLLB, using a novel subword compression module and Optimal Transport, while only utilizing ASR data. It thus enables **Zero-shot E2E Speech Translation to all the 200 languages supported by NLLB**.
257
 
@@ -326,9 +326,10 @@ BLEU scores on CoVoST-2 test compared to supervised SOTA models [XLS-R-1B](https
326
 
327
  | Models | ZS | Size (B) | Ar | Ca | Cy | De | Et | Fa | Id | Ja | Lv | Mn | Sl | Sv | Ta | Tr | Zh | Average |
328
  |:--------------:|:----:|:----------:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:-------:|
329
- | XLS-R-1B | ✗ | 1.0 | 19.2 | 32.1 | **31.8** | 26.2 | 22.4 | 21.3 | 30.3 | 39.9 | 22.0 | 14.9 | 25.4 | 32.3 | 18.1 | 17.1 | 36.7 | 26.0 |
330
- | SeamlessM4T-M | ✗ | 1.2 | 20.8 | 37.3 | 29.9 | **31.4** | 23.3 | 17.2 | 34.8 | 37.5 | 19.5 | 12.9 | 29.0 | 37.3 | 18.9 | **19.8** | 30.0 | 26.6 |
331
- | ZeroSwot-M_asr-cv | | 0.35/0.95 | **24.4** | **38.7** | 28.8 | 31.2 | **26.2** | **26.0** | **36.0** | **46.0** | **24.8** | **19.0** | **31.6** | **37.8** | **24.4** | 18.6 | **39.0** | **30.2** |
 
332
 
333
  ## Citation
334
 
 
251
 
252
  ZeroSwot is a state-of-the-art zero-shot end-to-end Speech Translation system.
253
 
254
+ <div align=center><img src="resources/intro.png" height="65%" width="65%"/></div>
255
 
256
  The model is created by adapting a wav2vec2.0-based encoder to the embedding space of NLLB, using a novel subword compression module and Optimal Transport, while only utilizing ASR data. It thus enables **Zero-shot E2E Speech Translation to all the 200 languages supported by NLLB**.
257
 
 
326
 
327
  | Models | ZS | Size (B) | Ar | Ca | Cy | De | Et | Fa | Id | Ja | Lv | Mn | Sl | Sv | Ta | Tr | Zh | Average |
328
  |:--------------:|:----:|:----------:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:-------:|
329
+ | [XLS-R-1B](https://huggingface.co/facebook/wav2vec2-xls-r-1b) | ✗ | 1.0 | 19.2 | 32.1 | **31.8** | 26.2 | 22.4 | 21.3 | 30.3 | 39.9 | 22.0 | 14.9 | 25.4 | 32.3 | 18.1 | 17.1 | 36.7 | 26.0 |
330
+ | [SeamlessM4T-Medium](https://huggingface.co/facebook/seamless-m4t-medium) | ✗ | 1.2 | 20.8 | 37.3 | 29.9 | **31.4** | 23.3 | 17.2 | 34.8 | 37.5 | 19.5 | 12.9 | 29.0 | 37.3 | 18.9 | **19.8** | 30.0 | 26.6 |
331
+ | [ZeroSwot-M_asr-cv](https://huggingface.co/johntsi/ZeroSwot-Medium_asr-cv_en-to-200) | | 0.35/0.95 | 17.6 | 32.5 | 18.0 | 29.9 | 20.4 | 16.3 | 32.4 | 32.0 | 13.3 | 10.0 | 25.2 | 34.4 | 17.8 | 15.6 | 30.5 | 23.1 |
332
+ | [ZeroSwot-M_asr-cv_mt-covost2](https://huggingface.co/johntsi/ZeroSwot-Medium_asr-cv_mt-covost2_en-to-200) | ✓ | 0.35/0.95 | **24.4** | **38.7** | 28.8 | 31.2 | **26.2** | **26.0** | **36.0** | **46.0** | **24.8** | **19.0** | **31.6** | **37.8** | **24.4** | 18.6 | **39.0** | **30.2** |
333
 
334
  ## Citation
335