jonatasgrosman / automatic-speech-recognition updated 3 years ago

wav2vec2-large-xlsr-53-japanese

Name: wav2vec2-large-xlsr-53-japanese
Author: jonatasgrosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz.

Params

—

Context

—

Downloads 30d

17.9 M

Likes

Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days

▲ 11.2 M in the last 30 days (168.5%)

17.9 M1.6 M

Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture: Wav2Vec2ForCTC
Vocabulary: 2,341
Layers / heads: 24 / 16
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: common_voice
Common Voice ja (reported): 20.16
Added to our catalog: 2026-07-28

Compare with any automatic-speech-recognition model

Popular comparisons

whisperkit-coreml 11.2 M speaker-diarization-3.1 8.2 M whisper-large-v3-turbo 6.8 M wav2vec2-large-xlsr-53-portuguese 6.0 M speaker-diarization-community-1 5.3 M whisper-large-v3 4.7 M