automatic-speech-recognition common_voice generated_from_trainer xls_r_repro_common_voice_tr

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

wav2vec2-xls-r-100m-common_voice-tr-ft

This model is a fine-tuned version of facebook/wav2vec2-xls-r-100m on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set:

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss Wer Cer
3.1315 9.09 500 3.3832 1.0 1.0
3.1163 18.18 1000 3.4252 1.0 1.0
3.121 27.27 1500 3.4051 1.0 1.0
3.1273 36.36 2000 3.4345 1.0 1.0
3.2257 45.45 2500 3.4097 1.0 1.0

Framework versions