wav2vec2-base-turkish-cv7

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

automatic-speech-recognition mozilla-foundation/common_voice_7_0 generated_from_trainer

This model is a fine-tuned version of cahya/wav2vec2-base-turkish-artificial on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - 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
1.8647 14.28 200 0.2758 0.2568
1.3376 28.56 400 0.2754 0.2722
1.1975 42.84 600 0.2929 0.2901
1.1024 57.14 800 0.2904 0.2928
1.0257 71.42 1000 0.2915 0.2823
0.9628 85.7 1200 0.2936 0.2749
0.9109 99.98 1400 0.2893 0.2713

Framework versions