espnet
/

geolid_combined_shared_trainable

language-identification

Model card Files Files and versions

Metrics Training metrics Community

qingzhengwang commited on Aug 19

Commit

2aa4505

·

1 Parent(s): 308b176

Update README

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ license: cc-by-4.0
 ### `espnet/geolid_combined_shared_trainable`
-This geolocation-aware language identification (LID) model is developed using the [ESPnet](https://github.com/espnet/espnet/) toolkit. It integrates the powerful pretrained MMS-1B model ([facebook/mms-1b](https://huggingface.co/facebook/mms-1b)) as the encoder and employs ECAPA-TDNN ([arXiv](https://arxiv.org/pdf/2005.07143)) as the embedding extractor to achieve robust spoken language identification.
 The main innovations of this model are:
 1. Incorporating geolocation prediction as an auxiliary task during training.

 ### `espnet/geolid_combined_shared_trainable`
+This geolocation-aware language identification (LID) model is developed using the [ESPnet](https://github.com/espnet/espnet/) toolkit. It integrates the powerful pretrained [MMS-1B](https://huggingface.co/facebook/mms-1b) as the encoder and employs [ECAPA-TDNN](https://arxiv.org/pdf/2005.07143) as the embedding extractor to achieve robust spoken language identification.
 The main innovations of this model are:
 1. Incorporating geolocation prediction as an auxiliary task during training.