Update README.md
Browse files
README.md
CHANGED
|
@@ -153,15 +153,16 @@ language:
|
|
| 153 |
---
|
| 154 |
|
| 155 |
[XEUS - A Cross-lingual Encoder for Universal Speech]()
|
|
|
|
| 156 |
|
| 157 |
XEUS is a large-scale multilingual speech encoder by Carnegie Mellon University's [WAVLab]() that covers over **4000** languages. It is pre-trained on over 1 million hours of publicly available speech datasets. It can be requires fine-tuning to be used in downstream tasks such as Speech Recognition or Translation. XEUS uses the [E-Branchformer]() architecture and is trained using [HuBERT]()-style masked prediction of discrete speech tokens extracted from [WavLabLM](). During training, the input speech is also augmented with acoustic noise and reverberation, making XEUS more robust. The total model size is 577M parameters.
|
| 158 |
|
|
|
|
|
|
|
| 159 |
XEUS tops the [ML-SUPERB]() multilingual speech recognition leaderboard, outperforming [MMS](), [w2v-BERT 2.0](), and [XLS-R](). XEUS also sets a new state-of-the-art on 4 tasks in the monolingual [SUPERB]() benchmark.
|
| 160 |
|
| 161 |
More information about XEUS, including ***download links for our crawled 4000-language dataset***, can be found in the [project page]().
|
| 162 |
|
| 163 |
-
|
| 164 |
-
|
| 165 |
|
| 166 |
## Requirements
|
| 167 |
|
|
|
|
| 153 |
---
|
| 154 |
|
| 155 |
[XEUS - A Cross-lingual Encoder for Universal Speech]()
|
| 156 |
+
|
| 157 |
|
| 158 |
XEUS is a large-scale multilingual speech encoder by Carnegie Mellon University's [WAVLab]() that covers over **4000** languages. It is pre-trained on over 1 million hours of publicly available speech datasets. It can be requires fine-tuning to be used in downstream tasks such as Speech Recognition or Translation. XEUS uses the [E-Branchformer]() architecture and is trained using [HuBERT]()-style masked prediction of discrete speech tokens extracted from [WavLabLM](). During training, the input speech is also augmented with acoustic noise and reverberation, making XEUS more robust. The total model size is 577M parameters.
|
| 159 |
|
| 160 |
+
|
| 161 |
+
|
| 162 |
XEUS tops the [ML-SUPERB]() multilingual speech recognition leaderboard, outperforming [MMS](), [w2v-BERT 2.0](), and [XLS-R](). XEUS also sets a new state-of-the-art on 4 tasks in the monolingual [SUPERB]() benchmark.
|
| 163 |
|
| 164 |
More information about XEUS, including ***download links for our crawled 4000-language dataset***, can be found in the [project page]().
|
| 165 |
|
|
|
|
|
|
|
| 166 |
|
| 167 |
## Requirements
|
| 168 |
|