PyTorch
ELM
hubert
ajesujoba commited on
Commit
6ddf5bf
·
verified ·
1 Parent(s): c90c8ed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -1241,10 +1241,10 @@ base_model:
1241
  ## AfriHuBERT: A self-supervised speech representation model for African languages
1242
 
1243
  ### Model description
1244
- This is a compact multilingual self-supervised speech encoder based on facebook/hubert-large-ll60k. We performed continued pretraining through multilingual adaptive finetuning (MAFT) on over 10,000 hours of African language data aggregated from various sources.
1245
 
1246
  ### Pretraining data
1247
- - Dataset: AfriHuBERT was trained on data from 11 major sources, including BibleTTS, Kallaama, MMS Ulab v2, NaijaVoices, and NCHLT. All sources and their licenses are shown in the table below. Please refer to the paper for more information.
1248
  ![Logo](images/afrihuberts_sources.png)
1249
 
1250
  ### Language Coverage
 
1241
  ## AfriHuBERT: A self-supervised speech representation model for African languages
1242
 
1243
  ### Model description
1244
+ This is a 300M+ parameter multilingual self-supervised speech encoder based on the English HuBERT-L model, facebook/hubert-large-ll60k. We performed continued pretraining through multilingual adaptive finetuning (MAFT) on over 10,000 hours of African language data aggregated from various sources.
1245
 
1246
  ### Pretraining data
1247
+ - Dataset: AfriHuBERT-large was trained on data from 11 major sources, including BibleTTS, Kallaama, MMS Ulab v2, NaijaVoices, and NCHLT. All sources and their licenses are shown in the table below. Please refer to the paper for more information.
1248
  ![Logo](images/afrihuberts_sources.png)
1249
 
1250
  ### Language Coverage