wav2vec2-xls-r-common_voice-tr-ft

作者 zhichao158 · 下载 0 · 点赞 1 · 更新 2023-10-31

automatic-speech-recognition common_voice generated_from_trainer

wav2vec2-xls-r-common_voice-tr-ft

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m 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
0.5462 13.51 500 0.4423 0.4807 0.1188
0.342 27.03 1000 0.3781 0.3954 0.0967
0.2272 40.54 1500 0.3816 0.3595 0.0893
0.1805 54.05 2000 0.3943 0.3487 0.0854
0.1318 67.57 2500 0.3818 0.3262 0.0801
0.1213 81.08 3000 0.3777 0.3113 0.0758
0.0639 94.59 3500 0.3788 0.2953 0.0716

Framework versions