comodoro / automatic-speech-recognition Open weights updated 4 years ago

wav2vec2-xls-r-300m-sk-cv8

Name: wav2vec2-xls-r-300m-sk-cv8
Author: comodoro

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the commonvoice 8.0 dataset. It achieves the following results on the evaluation set:

Params

300 M

Context

—

Downloads 30d

786 K

Likes

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

Download history

daily snapshots · 100 days

▲ 447 K in the last 30 days (131.5%)

918 K340 K

Aug 3Sep 5Oct 8Nov 10

Specifications

Architecture: Wav2Vec2ForCTC
Parameters: 300 M
Vocabulary: 49
Layers / heads: 24 / 16
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: common_voice
Common Voice 8 (reported): 13.3
Robust Speech Event - Dev Data (reported): 81.7
Robust Speech Event - Test Data (reported): 80.26
Added to our catalog: 2026-08-03

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 speaker-diarization-community-1 5.1 M wav2vec2-large-xlsr-53-russian 3.8 M