This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the COMMON_VOICE - AR dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Please use the evaluation script eval.py included in the repo.
speech-recognition-community-v2/dev_datapython eval.py --model_id nouamanetazi/wav2vec2-xls-r-300m-ar --dataset speech-recognition-community-v2/dev_data --config ar --split validation --chunk_length_s 5.0 --stride_length_s 1.0
pytorch_model.bin 1.3 GBlanguage_model/5gram.bin 10 MBtraining_args.bin 3.1 kB