Models
MODELHugging Face
4/5

MMS-TTS (per-lang)

Oroko(bdu)TTSVITS architecture
View Source

Model Info

Language
Oroko (bdu)
Architecture
VITS architecture
Institution
Meta AI (Pratap et al.)
Last Updated
14 May 2026

Intended Use Cases

TTS for 1107 languages

License & Access

SPDX identifierCC-BY-NC-4.0

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

Provenance

Fetch Timestamp
14 May 2026
Submitter
Meta AI (Pratap et al.)

Full Record

22 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 (16/18)

iso code
bdu
Model Name
MMS-TTS (per-lang)
Where is it hosted
HuggingFace
Link
https://huggingface.co/facebook/mms-tts
Year
2023
Creator/Author(s)
Meta AI (Pratap et al.)
Paper Reference
Pratap et al. 2023; arXiv:2305.13516
NLP Task
TTS
Architecture
Not stated
Base Model
VITS architecture
Fine-tuned?
Yes
License
CC-BY-NC-4.0
Open Access
Open
Has Model Card
Yes
SOTA Tasks
TTS for 1107 languages
Verified By
Not stated
Date Indexed
2026-05-14
Comment
Pratap et al. 2023 Meta AI

Readiness (LRS) (6/7)

model id
mms-tts-per-lang-bdu
Model Type
TTSderivedHugging Face card: pipeline_tag
Training Data Sources
Bible recordings + speech in 1107 languages
Benchmark Used
MMS TTS Evaluation (Biafada)derivedregistry benchmark records for this model
Benchmark Score
TTS evaluation for Biafada
Benchmark Date
2023
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.

Related Models