Hugging Face's logo

kmfoda
/
wav2vec2-large-xlsr-arabic

Automatic Speech Recognition Transformers PyTorch JAX
Arabic wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints
Model card Files Community
2
wav2vec2-large-xlsr-arabic / all_results.json
kmfoda's picture
kmfoda
First version of the wav2vec2-large-xlsr-arabice model and tokenizer.
30e4171
raw history blame contribute delete
No virus
771 Bytes
{
"epoch": 30.0,
"eval_loss": 1.1619502305984497,
"eval_mem_cpu_alloc_delta": 1765203650,
"eval_mem_cpu_peaked_delta": 70416270,
"eval_mem_gpu_alloc_delta": 0,
"eval_mem_gpu_peaked_delta": 5896910848,
"eval_runtime": 883.3879,
"eval_samples": 7622,
"eval_samples_per_second": 8.628,
"eval_wer": 0.6438685083419972,
"init_mem_cpu_alloc_delta": 620838,
"init_mem_cpu_peaked_delta": 18306,
"init_mem_gpu_alloc_delta": 1262070784,
"init_mem_gpu_peaked_delta": 0,
"train_mem_cpu_alloc_delta": 0,
"train_mem_cpu_peaked_delta": 0,
"train_mem_gpu_alloc_delta": 3788204544,
"train_mem_gpu_peaked_delta": 0,
"train_runtime": 115603.8298,
"train_samples": 21744,
"train_samples_per_second": 0.176
}