Data · dataset · 2022
The Cross-lingual TRansfer Evaluation of Multilingual Encoders for Speech (XTREME-S) benchmark is a benchmark designed to evaluate speech representations across languages, tasks, domains and data regimes. It covers 102 languages from 10+ language families, 3 different domains and 4 task families: speech recognition, translation, classification and retrieval.
Listed in Hugging Face Datasets
XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval.
Description
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.
Links
Where it is published
- Hugging Face dataset page huggingface.co/datasets/google/xtreme_s ↗
landing page · from Hugging Face
Documentation and papers
- arXiv:2203.10752 arxiv.org/abs/2203.10752 ↗
publication · from Hugging Face
- arXiv:2205.12446 arxiv.org/abs/2205.12446 ↗
publication · from Hugging Face
- arXiv:2101.00390 arxiv.org/abs/2101.00390 ↗
publication · from Hugging Face
- arXiv:2007.10310 arxiv.org/abs/2007.10310 ↗
publication · from Hugging Face
- arXiv:2104.08524 arxiv.org/abs/2104.08524 ↗
publication · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/google/xtreme_s ↗
metadata API · from Hugging Face
Topics
- Stated by source
- automatic speech recognition
- From keywords
- Computer Science & AI
- Inferred from text
- Audio 65%
Related
- Possibly the same asThe Cross-lingual TRansfer Evaluation of Multilingual Encoders for Speech (XTREME-S) benchmark is a benchmark designed to evaluate speech representations across languages, tasks, domains and data regimes. It covers 102 languages from 10+ language families, 3 different domains and 4 task families: speech recognition, translation, classification and retrieval.
- Possibly the same asThe Cross-lingual TRansfer Evaluation of Multilingual Encoders for Speech (XTREME-S) benchmark is a benchmark designed to evaluate speech representations across languages, tasks, domains and data regimes. It covers 102 languages from 10+ language families, 3 different domains and 4 task families: speech recognition, translation, classification and retrieval.
Provenance · 1 source records, 10 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | google/xtreme_s | 8 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].local:modality:audio | enrichment · Hugging Face | keyword-concept-rules@1.0.0 | title+description (65%) |
| concepts[task].hf_task:automatic-speech-recognition | source · Hugging Face | connector:huggingface@1.0.0 | /tags[task_categories:*] |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| license | source · Hugging Face | connector:huggingface@1.0.0 | /tags[license:*] |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |