Instructions to use espnet/xeus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/xeus with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/xeus" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Update README.md
Browse files
README.md
CHANGED
|
@@ -158,6 +158,8 @@ language:
|
|
| 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 |
## Requirements
|
| 162 |
|
| 163 |
The code for XEUS is still in progress of being merged into the main ESPnet repo. It can instead be used from the following fork:
|
|
|
|
| 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 links to our crawled 4000-language dataset, can be found in the [project page]().
|
| 162 |
+
|
| 163 |
## Requirements
|
| 164 |
|
| 165 |
The code for XEUS is still in progress of being merged into the main ESPnet repo. It can instead be used from the following fork:
|