Models
MODELHugging Face
5/5

UBC-NLP/Simba-M

Malagasy(mlg)ASRSimba (Whisper fine-tune)Encoder (Whisper-based)
View Source

Model Info

Language
Malagasy (mlg)
Architecture
Encoder (Whisper-based)
Institution
UBC-NLP (University of British Columbia NLP Group)
Last Updated
9 Jun 2026

Intended Use Cases

ASR (African languages incl. Malagasy)

License & Access

SPDX identifiercc-by-4.0

Open — attribution required; commercial use allowed.

Provenance

Fetch Timestamp
9 Jun 2026
Submitter
UBC-NLP (University of British Columbia NLP Group)

Full Record

21 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
mlg
Model Name
UBC-NLP/Simba-M
Where is it hosted
HuggingFace
Link
https://huggingface.co/UBC-NLP/Simba-M
Year
2025
Creator/Author(s)
UBC-NLP (University of British Columbia NLP Group)
Paper Reference
UBC-NLP (2025). Simba: Multilingual African ASR/TTS Models. HuggingFace.
NLP Task
ASR
Architecture
Encoder (Whisper-based)
Base Model
Simba (Whisper fine-tune)
Fine-tuned?
Yes
License
cc-by-4.0
Open Access
Open
Has Model Card
Yes
SOTA Tasks
ASR (African languages incl. Malagasy)
Verified By
Not stated
Date Indexed
2026-06-09
Comment
Malagasy (mlg) included in Simba-M multilingual African ASR model from UBC-NLP. Part of Simba family (Simba-S, Simba-W, Simba-X, Simba-H, Simba-M).

Readiness (LRS) (4/7)

model id
ubc-nlp-simba-m-mlg
Model Type
ASR
Training Data Sources
SimbaBench multilingual African corpus
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

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesAmharic(amh)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesArabic(ara)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesBambara(bam)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesDinka(din)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesEwe(ewe)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesHausa(hau)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesIgbo(ibo)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesKinyarwanda(kin)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesKongo(kon)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesLingala(lin)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesLuba-Katanga(lub)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesLuganda(lug)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesLuo(luo)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesMooré(mos)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesNorthern Sotho(nso)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesChewa(nya)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesOromo(orm)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesSango(sag)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesShona(sna)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026
model

Simba-M

automatic-speech-recognition model · Wav2Vec2ForCTC · UBC-NLP

35 languagesSomali(som)Wav2Vec2ForCTCautomatic-speech-recognition
HUHugging Face
Open27 Oct 2026

Related Models