nouamanetazi
/

wav2vec2-xls-r-300m-ar

Automatic Speech Recognition Transformers PyTorch

Arabic wav2vec2 common_voice generated_from_trainer hf-asr-leaderboard robust-speech-event Eval Results Inference Endpoints

Model card Files Files and versions Community

wav2vec2-xls-r-300m-ar

File size: 230 Bytes

c130393
ac5fb9c
 
 
 
c130393
ac5fb9c
 
c130393

{
    "epoch": 20.0,
    "total_flos": 5.430583918308557e+17,
    "train_loss": 8.69529299736023,
    "train_runtime": 243.8197,
    "train_samples": 128,
    "train_samples_per_second": 10.5,
    "train_steps_per_second": 0.164
}