Models
MODELHugging Face
5/5

SalahZa Code-Switched Tunisian ASR

Tunisian Arabic(aeb)ASRwav2vec 2.0
View Source

Model Info

Language
Tunisian Arabic (aeb)
Architecture
wav2vec 2.0
Institution
SalahZa (individual contributor)
Last Updated
12 May 2026

Intended Use Cases

Code-switched Tunisian-French/English ASR

License & Access

SPDX identifierapache-2.0

Open — attribution required; commercial use allowed.

Provenance

Fetch Timestamp
12 May 2026
Submitter
SalahZa (individual contributor)

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 (15/18)

iso code
aeb
Model Name
SalahZa Code-Switched Tunisian ASR
Where is it hosted
HuggingFace
Link
https://huggingface.co/SalahZa/Code_Switched_Tunisian_Speech_Recognition
Year
2023
Creator/Author(s)
SalahZa (individual contributor)
Paper Reference
https://arxiv.org/abs/2309.11327derivedHugging Face card: arXiv tag
NLP Task
ASR
Architecture
Not stated
Base Model
wav2vec 2.0
Fine-tuned?
Yes
License
apache-2.0derivedHugging Face card: license
Open Access
Open
Has Model Card
Yes
SOTA Tasks
Code-switched Tunisian-French/English ASR
Verified By
Not stated
Date Indexed
2026-05-12
Comment
Not stated

Readiness (LRS) (2/7)

model id
salahza-code-switched-tunisian-asr-aeb
Model Type
Not stated
Training Data Sources
Tunisian Arabic + French/English code-switched audio
Benchmark Used
Not stated
Benchmark Score
Not stated
Benchmark Date
Not stated
Status
Not stated

Readiness Score Breakdown

5/5
Data Coverage100%
Model Availability100%
Benchmarks100%
Documentation78%
Recency100%

Representativeness

Gender Balance
Regional Distribution
Dialect Coverage
Inclusivity
Relations Explorer link

Related Models