MODELHugging Face

4/5

MMS-1B-L1107 (ASR)

Oroko(bdu)ASRfacebook/mms-1bWav2Vec2ForCTC

Model Info

Language

Oroko (bdu)

Architecture

Wav2Vec2ForCTC

Institution

Meta AI (Pratap et al.)

Last Updated

14 May 2026

Intended Use Cases

ASR on Bible-domain low-resource languages

License & Access

SPDX identifierCC-BY-NC-4.0

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

Provenance

Source URL

https://huggingface.co/facebook/mms-1b-l1107

Fetch Timestamp

14 May 2026

Submitter

Meta AI (Pratap et al.)

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: bdu
Model Name: MMS-1B-L1107 (ASR)
Where is it hosted: HuggingFace
Link: https://huggingface.co/facebook/mms-1b-l1107
Year: 2023
Creator/Author(s): Meta AI (Pratap et al.)
Paper Reference: Pratap et al. 2023; arXiv:2305.13516
NLP Task: ASR
Architecture: Wav2Vec2ForCTCderivedHugging Face config: architectures / model_type
Base Model: facebook/mms-1b
Fine-tuned?: Yes
License: CC-BY-NC-4.0
Open Access: Open
Has Model Card: Yes
SOTA Tasks: ASR on Bible-domain low-resource languages
Verified By: Not stated
Date Indexed: 2026-05-14
Comment: Pratap et al. 2023 Meta AI; arXiv:2305.13516

Readiness (LRS) (3/7)

model id: mms-1b-l1107-asr-bdu
Model Type: ASRderivedHugging Face card: pipeline_tag
Training Data Sources: Bible recordings in 1107 languages (MMS-lab)
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Not stated

Readiness Score Breakdown

4/5

Data Coverage72%

Model Availability100%

Benchmarks33%

Documentation75%

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.

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesAfrikaans(afr)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesAkan(aka)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesAmharic(amh)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesArabic(ara)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesBambara(bam)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

MMS-1B-L1107 (ASR)

Pratap et al. 2023 Meta AI; arXiv:2305.13516

31 languagesBari(bfa)facebook/mms-1bASR

Open14 May 2026

MMS-1B-L1107 (ASR)

Pratap et al. 2023 Meta AI; arXiv:2305.13516

31 languagesMalba Birifor(bfo)facebook/mms-1bASR

Open14 May 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesEwe(ewe)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesFula(ful)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesHausa(hau)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesIgbo(ibo)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesKanuri(kau)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesGikuyu(kik)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesKinyarwanda(kin)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesLingala(lin)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesLuganda(lug)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesMalagasy(mlg)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesChewa(nya)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesOromo(orm)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

mms-1b-l1107

automatic-speech-recognition model · Wav2Vec2ForCTC · facebook

31 languagesKirundi(run)Wav2Vec2ForCTCautomatic-speech-recognition

Restricted27 Oct 2026

Related Models

MMS-TTS (per-lang)

Pratap et al. 2023 Meta AI

3 languagesOroko(bdu)VITS architectureTTS

Open14 May 2026

MMS-LID-4017

Pratap et al. 2023 Meta AI

31 languagesOroko(bdu)facebook/mms-1bClassification (LID)

Open14 May 2026

GlotLID-M

Likely covers most of these languages via Bible portions; verify per-language

550 languages2 copiesOroko(bdu)FastTextClassification (LID)

Open14 May 2026