Downloads · 30 days
22
1% of all-time downloads
wav2vec2-base-da
Alvenir/wav2vec2-base-da
wav2vec2-base-da is a machine learning model from Alvenir. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we were allowed to distri…
All-time downloads
3.8K
Public
Repo size
760 MB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.bin380 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Nov 28, 2021
- SHA
- 91200248
Model card
From the Hugging Face model README
Wav2vec2-base for Danish
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we were allowed to distribute the pretrained model.
This model was pretrained on 16kHz sampled speech audio. When using the model, make sure to use speech audio sampled at 16kHz.
The pre-training was done using the fairseq library in January 2021.
It needs to be fine-tuned to perform speech recognition.
Finetuning
In order to finetune the model to speech recognition, you can draw inspiration from this notebook tutorial or this blog post tutorial.
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- da
- Created
- Mar 2, 2022
- Updated
- Nov 28, 2021