indonesian-nlp / automatic-speech-recognition Open weights updated 4 years ago

wav2vec2-indonesian-javanese-sundanese

Name: wav2vec2-indonesian-javanese-sundanese
Author: indonesian-nlp

This is the model built for the project Multilingual Speech Recognition for Indonesian Languages. It is a fine-tuned facebook/wav2vec2-large-xlsr-53 model on the Indonesian Common Voice dataset, High-quality TTS data for Javanese - SLR41, and High-quality TTS data for Sundanese - SLR44 datasets.

Params

—

Context

—

Downloads 30d

1.7 M

Likes

Commercial use: allowed apache-2.0 Not gated 3 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 96 K in the last 30 days (5.2%)

3.7 M1.3 M

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: Wav2Vec2ForCTC
Vocabulary: 30
Layers / heads: 24 / 16
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: mozilla-foundation/common_voice_7_0, openslr, magic_data, titml
Common Voice 7 (reported): 1.577
Common Voice 6.1 (reported): 1.472
Robust Speech Event - Dev Data (reported): 48.94
Robust Speech Event - Test Data (reported): 68.95
Added to our catalog: 2026-07-28

Compare with any automatic-speech-recognition model

Popular comparisons

whisperkit-coreml 51.6 M wav2vec2-large-xlsr-53-japanese 16.2 M speaker-diarization-3.1 6.7 M faster-whisper-small 5.7 M whisper-large-v3-turbo 5.2 M speaker-diarization-community-1 5.1 M