wav2vec2-bert-CV16-de

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - DE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.095182
  • Wer: 0.066672
  • Steps: 25000
  • epoch: 10
Downloads last month
3
Safetensors
Model size
606M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Dataset used to train sharrnah/wav2vec2-bert-CV16-de