Models
MODELHugging Face
5/5

facebook/mms-1b-all (dik ASR adapter)

Dinka (Southwestern)(dik)ASR / wav2vec 2.0 with language adapterswav2vec 2.0 1BWav2Vec2ForCTC
View Source

Model Info

Language
Dinka (Southwestern) (dik)
Architecture
Wav2Vec2ForCTC
Institution
Vineel Pratap et al. (Meta AI)
Last Updated
25 May 2026

Intended Use Cases

ASR for 1162 languages including dik (Bible domain)

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-all
Fetch Timestamp
25 May 2026
Submitter
Vineel Pratap et al. (Meta AI)

Full Record

23 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
dik
Model Name
facebook/mms-1b-all (dik ASR adapter)
Where is it hosted
HuggingFace
Link
https://huggingface.co/facebook/mms-1b-all
Year
2023
Creator/Author(s)
Vineel Pratap et al. (Meta AI)
Paper Reference
Pratap et al. (2023) Scaling Speech Technology to 1,000+ Languages. arXiv:2305.13516
NLP Task
ASR / wav2vec 2.0 with language adapters
Architecture
Wav2Vec2ForCTCderivedHugging Face config: architectures / model_type
Base Model
wav2vec 2.0 1B
Fine-tuned?
No
License
CC-BY-NC 4.0
Open Access
Open
Has Model Card
Yes
SOTA Tasks
ASR for 1162 languages including dik (Bible domain)
Verified By
Not stated
Date Indexed
2026-05-25
Comment
MMS 1B ASR model with language-specific adapter for Southwestern Dinka (dik). Per-language WER reported in paper. Activate dik adapter for best performance. Bib…

Readiness (LRS) (6/7)

model id
facebook-mms-1b-all-dik-asr-adapter-dik
Model Type
ASRderivedHugging Face card: pipeline_tag
Training Data Sources
MMS-lab multilingual speech (1162 languages)
Benchmark Used
MMS ASR Benchmark (Biafada adapter)derivedregistry benchmark records for this model
Benchmark Score
ASR WER for Biafada
Benchmark Date
2023
Status
Not stated

Readiness Score Breakdown

5/5
Data Coverage100%
Model Availability100%
Benchmarks100%
Documentation92%
Recency100%

Representativeness

Gender Balance
Regional Distribution
Dialect Coverage
Inclusivity
Relations Explorer link

Related Models

model

facebook/mms-tts-dik

Meta MMS-TTS VITS model for Southwestern Dinka (dik). Part of MMS project (1100+ languages). Available via HuggingFace Transformers >=4.33. Input: text; Outp…

Dinka (Southwestern)(dik)VITS (Variational Inference with adversarial learning for TTS)TTS / VITS end-to-end
HUHugging Face
Open25 May 2026
model

google/madlad400-3b-mt

3B-parameter multilingual MT model covering 400+ languages including Southwestern Dinka. Also available: 7B and 10B variants. Verify Dinka dialect coverage i…

87 languages3 copiesDinka (Southwestern)(dik)T5MT / Encoder-Decoder
HUHugging Face
Open25 May 2026
model

xeus

automatic-speech-recognition model · espnet · espnet

1,424 languagesDinka (Southwestern)(dik)espnetautomatic-speech-recognition
HUHugging Face
Restricted27 Oct 2026