MODELHugging Face

5/5

xeus

Bemba(bem)automatic-speech-recognitionespnet

View Source

Model Info

Language

Bemba (bem)

Architecture

espnet

Institution

espnet

Last Updated

27 Oct 2026

Intended Use Cases

automatic-speech-recognition

License & Access

SPDX identifiercc-by-nc-sa-4.0

Open with restrictions — attribution required; some commercial or derivative use limited.

Provenance

Source URL

https://huggingface.co/espnet/xeus

Fetch Timestamp

27 Oct 2026

Submitter

espnet

Full Record

17 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (13/18)

iso code: bem
Model Name: xeus
Where is it hosted: Hugging Face
Link: https://huggingface.co/espnet/xeus
Year: 2024
Creator/Author(s): espnet
Paper Reference: https://arxiv.org/abs/2210.00077
NLP Task: automatic-speech-recognition
Architecture: espnet
Base Model: Not stated
Fine-tuned?: Not stated
License: cc-by-nc-sa-4.0
Open Access: Restricted
Has Model Card: Yes
SOTA Tasks: Not stated
Verified By: Not stated
Date Indexed: 2026-10-27
Comment: Not stated

Readiness (LRS) (4/7)

model id: xeus-bem
Model Type: ASR
Training Data Sources: espnet/yodas, facebook/voxpopuli, facebook/multilingual_librispeech, google/fleurs, openslr/librispeech_asr, speechcolab/gigaspeech, cheulyop/ksponspeech, espne…derivedHugging Face card: datasets
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Activederivedupdated within 3 years

Readiness Score Breakdown

5/5

Data Coverage100%

Model Availability100%

Benchmarks100%

Documentation86%

Recency100%

Representativeness

Gender Balance

Regional Distribution

Dialect Coverage

Inclusivity

Relations Explorer link

Also Available In

This is the same multilingual corpus, sliced for other languages the platform indexes it under.

model

xeus

automatic-speech-recognition model · espnet · espnet

1,424 languagesGhotuo(aaa)espnetautomatic-speech-recognition

HUHugging Face

Restricted27 Oct 2026

model

xeus

automatic-speech-recognition model · espnet · espnet

1,424 languagesAlumu-Tesu(aab)espnetautomatic-speech-recognition

HUHugging Face

Restricted27 Oct 2026

model

xeus

automatic-speech-recognition model · espnet · espnet

1,424 languagesAfade(aal)espnetautomatic-speech-recognition

HUHugging Face

Restricted27 Oct 2026

model

espnet/xeus

Relevant to aao: HuggingFace language filter shows one aao model, espnet/xeus; model covers 4,024 languages and can be fine-tuned for Algerian Saharan Arabic…

1,424 languagesAlgerian Saharan Arabic(aao)XEUS self-supervised speech encoder (577M parameters)ASR / speech representation learning; E-Branchformer encoder; HuBERT-style masked prediction

HUHugging Face

Open11 May 2026

model

espnet/xeus

Large-scale multilingual speech encoder pre-trained on 4,057 languages. Afar likely included among 4,057 languages (not explicitly confirmed). Uses HuBERT-st…

1,424 languagesAfar(aar)E-BranchformerASR

HUHugging Face

Open11 May 2026

model