jonatasgrosman / automatic-speech-recognition Open weights updated 3 years ago

wav2vec2-large-xlsr-53-chinese-zh-cn

Name: wav2vec2-large-xlsr-53-chinese-zh-cn
Author: jonatasgrosman

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

Params

—

Context

—

Downloads 30d

1.9 M

Likes

149

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

Download history

daily snapshots · 106 days

▲ 281 K in the last 30 days (17.7%)

2.0 M1.2 M

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: Wav2Vec2ForCTC
Vocabulary: 3,503
Layers / heads: 24 / 16
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: common_voice
Common Voice zh-CN (reported): 19.03
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