Downloads · 30 days
0
waxal-benchmarking/omniasr-llm-300m-waxal-all19
omniasr-llm-300m-waxal-all19 is a automatic speech recognition model from waxal-benchmarking. Use it when you need speech turned into text. It is set up for fairseq2. The card lists the license as cc-by-4.0.
A all 19 WAXAL languages (multilingual) multilingual fine-tune of Meta's Omnilingual ASR (wav2vec2llama, 300M-parameter shared wav2vec2 encoder + autoregressive Llama-style decoder), trained jointly on 19 WAXAL langua…
Downloads · 30 days
0
Access
Public
Updated Oct 16, 2026
Repo size
3.3 GB
Likes
1
Public
Click a slice to open those files.
.pt3.3 GB · 100%
From the Hugging Face model README
A all 19 WAXAL languages (multilingual) multilingual fine-tune of Meta's Omnilingual ASR (wav2vec2_llama,
300M-parameter shared wav2vec2 encoder + autoregressive Llama-style decoder), trained
jointly on 19 WAXAL languages. Part of the WAXAL ASR benchmark's
training-granularity study (monolingual vs. language-family vs. all-19 pooling).
facebook/omniASR-LLM-300MFine-tuned on the pooled train splits of the WAXAL corpus for these languages (16 kHz mono; transcripts NFC-normalized and lower-cased, punctuation removed, phonemic diacritics/tone marks preserved). Total: 362,117 clips / 1857.7 hours.
| Language | Train clips | Train hours |
|---|---|---|
| Acholi | 4,108 | 25.8 |
| Akan | 10,107 | 55.0 |
| Amharic | 38,022 | 189.7 |
| Dagbani | 14,231 | 77.0 |
| Dagaare | 15,071 | 83.4 |
| Ewe | 15,052 | 79.5 |
| Fula | 19,132 | 99.7 |
| Ikposo | 14,415 | 82.1 |
| Lingala | 14,399 | 71.9 |
| Luganda | 5,455 | 37.3 |
| Masaaba | 6,865 | 39.3 |
| Malagasy | 18,526 | 94.7 |
| Nyankole | 6,783 | 40.8 |
| Oromo | 38,182 | 189.9 |
| Sidama | 38,752 | 192.7 |
| Shona | 14,109 | 79.7 |
| Soga | 6,219 | 40.0 |
| Tigrinya | 40,856 | 181.9 |
| Wolaytta | 41,833 | 197.3 |
Fine-tuned with the Omnilingual-ASR wav2vec2_llama recipe (fairseq2) on 2× NVIDIA H200
(DistributedDataParallel). All granularity conditions use an identical budget so the only
variable is the language mixture.
| Hyperparameter | Value |
|---|---|
| Base checkpoint | facebook/omniASR-LLM-300M |
| Tokenizer | omniASR_tokenizer_v1 (SentencePiece, 9,812 units) |
| Training steps | 5,000 |
| Optimizer | AdamW |
| Learning rate | 5e-5 |
| Weight decay | 0.01 |
| Batch size | 3,000,000 audio tokens/batch (dynamic) |
| Gradient accumulation | 4 |
| Precision | bfloat16 mixed |
| Audio length filter | 0.5 s – 30 s |
| Hardware | 2× H200 (DDP) |
Scored on each language's held-out test split (utterances ≥ 1.5 s, matching the
benchmark's filtered-test protocol). WER and CER computed with jiwer on NFC-normalized,
lower-cased text (diacritics preserved). The Monolingual WER column is the corresponding
per-language model (omniasr-llm-300m-waxal-<iso>)
evaluated identically, for a same-protocol comparison.
| Language | Code | WER | CER | Monolingual WER | Δ vs mono |
|---|---|---|---|---|---|
| Acholi | ach_Latn | 33.2 | 13.7 | 33.3 | -0.1 |
| Akan | aka_Latn | 29.1 | 9.8 | 29.2 | -0.1 |
| Amharic | amh_Ethi | 26.9 | 10.7 | 25.0 | +1.9 |
| Dagbani | dag_Latn | 34.0 | 11.6 | 31.2 | +2.8 |
| Dagaare | dga_Latn | 32.2 | 13.0 | 29.0 | +3.2 |
| Ewe | ewe_Latn | 29.8 | 9.4 | 29.0 | +0.8 |
| Fula | ful_Latn | 36.5 | 9.5 | 39.1 | -2.6 |
| Ikposo | kpo_Latn | 72.5 | 24.6 | 69.2 | +3.2 |
| Lingala | lin_Latn | 29.9 | 12.5 | 30.4 | -0.5 |
| Luganda | lug_Latn | 12.1 | 2.8 | 10.9 | +1.1 |
| Masaaba | myx_Latn | 45.1 | 10.2 | 45.5 | -0.5 |
| Malagasy | mlg_Latn | 12.9 | 3.4 | 11.4 | +1.5 |
| Nyankole | nyn_Latn | 32.2 | 8.4 | 32.3 | -0.1 |
| Oromo | orm_Latn | 22.8 | 6.0 | 20.9 | +2.0 |
| Sidama | sid_Latn | 30.5 | 7.5 | 28.7 | +1.8 |
| Shona | sna_Latn | 21.6 | 3.9 | 21.6 | +0.0 |
| Soga | xog_Latn | 42.7 | 8.5 | 42.8 | -0.1 |
| Tigrinya | tir_Ethi | 40.6 | 17.4 | 37.0 | +3.7 |
| Wolaytta | wal_Latn | 40.0 | 11.7 | 36.7 | +3.2 |
# pip install git+https://github.com/facebookresearch/omnilingual-asr.git
from pathlib import Path
import torch
from huggingface_hub import snapshot_download
from fairseq2.data.tokenizers.hub import load_tokenizer
from omnilingual_asr.models.inference.pipeline import ASRInferencePipeline
from omnilingual_asr.models.wav2vec2_llama.hub import get_wav2vec2_llama_model_hub
ckpt = snapshot_download("waxal-benchmarking/omniasr-llm-300m-waxal-all19")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dtype = torch.bfloat16 if device.type == "cuda" else torch.float32
hub = get_wav2vec2_llama_model_hub()
model = hub.load_custom_model(Path(ckpt) / "model", hub.get_arch_config("300m"), device=device, dtype=dtype)
tokenizer = load_tokenizer("omniASR_tokenizer_v1")
pipe = ASRInferencePipeline(model_card=None, model=model, tokenizer=tokenizer, device=device, dtype=dtype)
# pass the target language's Omnilingual token, e.g. Acholi -> "ach_Latn"
texts = pipe.transcribe(["your_audio.flac"], lang=["ach_Latn"])
print(texts)
Language tokens for this model: Acholi ach_Latn, Akan aka_Latn, Amharic amh_Ethi, Dagbani dag_Latn, Dagaare dga_Latn, Ewe ewe_Latn, Fula ful_Latn, Ikposo kpo_Latn, Lingala lin_Latn, Luganda lug_Latn, Masaaba myx_Latn, Malagasy mlg_Latn, Nyankole nyn_Latn, Oromo orm_Latn, Sidama sid_Latn, Shona sna_Latn, Soga xog_Latn, Tigrinya tir_Ethi, Wolaytta wal_Latn.
Audio should be mono 16 kHz (the pipeline resamples if needed); keep clips under 40 s.
Native fairseq2 sharded checkpoint (model/pp_00/tp_00/sdp_00.pt + model.yaml) —
not a transformers model, so AutoModel will not load it. Load with omnilingual_asr /
fairseq2 as shown above.
Intended use. Research on, and development of, speech recognition for the language(s) this model was trained on, in particular for low-resource and under-served language communities. Error rates are still too high for high-stakes uses such as healthcare, legal, or emergency settings without further validation on the target domain.
Prohibited uses. This model must not be used for non-consensual applications, including surveillance or monitoring of individuals or communities, covert recording or transcription of people without their consent, or voice cloning and impersonation. Please respect the consent and privacy of the speakers whose speech you process.
Part of the WAXAL ASR Benchmark (arXiv:2606.02375).
@article{waxalnet2026,
title = {The WAXAL ASR Benchmark: Fine-Tuned Edge Models Across 19 African Languages},
author = {Olufemi, Victor Tolulope and Babatunde, Oreoluwa and Njema, Ramsey and others},
year = {2026},
note = {arXiv preprint arXiv:2606.02375}
}
Supported by Lynguallabs (compute, researchers & storage), Open Token (compute), and CMU Africa (researchers & native speakers).