A monolingual automatic speech recognition model for
Lingala
, fine-tuned from
openai/whisper-large-v3
. Part of
BuzzASR
,
a suite of 102 language-specialized ASR models (Findings of EMNLP 2026).
This model uses
simple fine-tuning (Whisper's tokenizer, ASR fine-tuning only)
.
Results (normalized CER / WER, %)
Test set
CER
WER
Whisper-large-v3 (zero-shot) CER
FLEURS
7.42
21.52
18.58
Combined
7.42
21.52
18.58
~2.5x CER reduction over Whisper zero-shot on the combined test set.
lingala huggingface.co is an AI model on huggingface.co that provides lingala's model effect (), which can be used instantly with this BuzzASR lingala model. huggingface.co supports a free trial of the lingala model, and also provides paid use of the lingala. Support call lingala model through api, including Node.js, Python, http.
lingala huggingface.co is an online trial and call api platform, which integrates lingala's modeling effects, including api services, and provides a free online trial of lingala, you can try lingala online for free by clicking the link below.
BuzzASR lingala online free url in huggingface.co:
lingala is an open source model from GitHub that offers a free installation service, and any user can find lingala on GitHub to install. At the same time, huggingface.co provides the effect of lingala install, users can directly use lingala installed effect in huggingface.co for debugging and trial. It also supports api for free installation.