A monolingual automatic speech recognition model for
Luo
, 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
9.32
35.85
35.85
Common Voice 25
95.04
88.63
34.17
Combined
76.92
77.47
34.34
~0.4x CER reduction over Whisper zero-shot on the combined test set.
luo huggingface.co is an AI model on huggingface.co that provides luo's model effect (), which can be used instantly with this BuzzASR luo model. huggingface.co supports a free trial of the luo model, and also provides paid use of the luo. Support call luo model through api, including Node.js, Python, http.
luo huggingface.co is an online trial and call api platform, which integrates luo's modeling effects, including api services, and provides a free online trial of luo, you can try luo online for free by clicking the link below.
luo is an open source model from GitHub that offers a free installation service, and any user can find luo on GitHub to install. At the same time, huggingface.co provides the effect of luo install, users can directly use luo installed effect in huggingface.co for debugging and trial. It also supports api for free installation.