aioxlabs/dvoice-wolof

Wolof(wol)ASRfacebook/wav2vec2-large-xlsr-53Encoder (wav2vec 2.0 + DNN)

View Source

Model Info

Language

Wolof (wol)

Architecture

Encoder (wav2vec 2.0 + DNN)

Institution

AIOX Labs; SI2M Laboratory

Last Updated

1 Jul 2026

Intended Use Cases

ASR (Wolof)

License & Access

SPDX identifierCC-BY-4.0

Open — attribution required; commercial use allowed.

Provenance

Source URL

https://huggingface.co/aioxlabs/dvoice-wolof

Fetch Timestamp

1 Jul 2026

Submitter

AIOX Labs; SI2M Laboratory

Full Record

20 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 (17/18)

iso code: wol
Model Name: aioxlabs/dvoice-wolof
Where is it hosted: HuggingFace
Link: https://huggingface.co/aioxlabs/dvoice-wolof
Year: 2022
Creator/Author(s): AIOX Labs; SI2M Laboratory
Paper Reference: DVoice project (2022). Collecting Resources in Sub-Saharan African Languages for ASR: a Case Study of Wolof.
NLP Task: ASR
Architecture: Encoder (wav2vec 2.0 + DNN)
Base Model: facebook/wav2vec2-large-xlsr-53
Fine-tuned?: Yes
License: CC-BY-4.0
Open Access: Open
Has Model Card: Yes
SOTA Tasks: ASR (Wolof)
Verified By: Not stated
Date Indexed: 2026-07-01
Comment: Wolof ASR model from DVoice initiative. Fine-tuned wav2vec2-XLSR-53 on Wolof speech data from Common Voice platform + social media recordings.

Readiness (LRS) (3/7)

model id: aioxlabs-dvoice-wolof-wol
Model Type: ASR
Training Data Sources: DVoice Wolof ASR dataset (Common Voice + social media)
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Not stated