sharrnah
/

wav2vec2-bert-CV16-de

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Community

Edit model card

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: 135

Safetensors

Model size

606M params

Tensor type

F32

·

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