Commit
β’
9594d68
1
Parent(s):
37e13fc
Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,49 @@
|
|
1 |
---
|
2 |
title: README
|
3 |
-
emoji:
|
4 |
colorFrom: indigo
|
5 |
-
colorTo:
|
6 |
sdk: static
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
title: README
|
3 |
+
emoji: π
|
4 |
colorFrom: indigo
|
5 |
+
colorTo: yellow
|
6 |
sdk: static
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
<div class="grid lg:grid-cols-3 gap-x-4 gap-y-7">
|
11 |
+
<p class="lg:col-span-3">
|
12 |
+
XTREME-S is a benchmark for evaluating universal cross-lingual speech representations in many languages. XTREME-S consists of:
|
13 |
+
</p>
|
14 |
+
<a
|
15 |
+
href="https://arxiv.org/abs/2203.10752"
|
16 |
+
class="block overflow-hidden"
|
17 |
+
>
|
18 |
+
<div class="flex items-center h-40 rounded-lg px-4 mb-2" style="background-color: #FAFBFC;">
|
19 |
+
<pre
|
20 |
+
class="break-words leading-1 whitespace-pre-line text-xl text-gray-800">
|
21 |
+
π Paper
|
22 |
+
</pre>
|
23 |
+
</div>
|
24 |
+
</a>
|
25 |
+
<a href="https://huggingface.co/datasets/xtreme-s/datasets" class="block overflow-hidden group">
|
26 |
+
<div class="flex items-center h-40 rounded-lg px-4 mb-2" style="background-color: #FAFBFC;">
|
27 |
+
<pre
|
28 |
+
class="break-words leading-1 whitespace-pre-line text-xl text-gray-800">
|
29 |
+
π€ Datasets
|
30 |
+
</pre>
|
31 |
+
</div>
|
32 |
+
</a>
|
33 |
+
<a
|
34 |
+
href="https://huggingface.co/spaces/xtreme-s/leaderboard"
|
35 |
+
class="block overflow-hidden group"
|
36 |
+
>
|
37 |
+
<div class="flex items-center h-40 rounded-lg px-4 mb-2" style="background-color: #FAFBFC;">
|
38 |
+
<pre
|
39 |
+
class="break-words leading-1 whitespace-pre-line text-xl text-gray-800">
|
40 |
+
π Leaderboard
|
41 |
+
</pre>
|
42 |
+
</div>
|
43 |
+
</a>
|
44 |
+
<p class="lg:col-span-3">
|
45 |
+
XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval. Covering 102 languages from 10+ language families, 3 different domains and 4 task families, XTREME-S aims to simplify multilingual speech representation evaluation, as well as catalyze research in "universal" speech representation learning.
|
46 |
+
|
47 |
+
XTREME-S was proposed in the paper *XTREME-S: Evaluating Cross-lingual Speech Representations* by Conneua et. al. in 2022.
|
48 |
+
</p>
|
49 |
+
</div>
|