# PreTrain Wav2Vec2 in German
**URL:**
**Author:**  [@patrickvonplaten](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpatrickvonplaten)%5C
**Post date:** [June 28, 2021, 8:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F1 "2021-06-28T20:55:26Z")
# PreTrain Wav2Vec2 in German
There is currently only a multilingually pretrained model for German Wav2Vec2. Let’s make a Wav2Vec2 only pretrained on German.
## Model
A randomly initialized Wav2Vec2 model
## Datasets
One can make use [Common Voice](https://commonvoice.mozilla.org/en/languages) the dataset is also available through the `datasets` library here: [https://huggingface.co/datasets/common\_voice](https://huggingface.co/datasets/common_voice).
## Available training scripts
FlaxWav2Vec2 will be merged soon: [https://github.com/huggingface/transformers/pull/12271](https://github.com/huggingface/transformers/pull/12271) and a pretraining script should be relatively easy to be merged.
## (Optional) Desired project outcome
The best German ASR model.
## (Optional) Challenges
It might make sense to use more data than just common voice.
---
**Author:**  [@patrickvonplaten](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpatrickvonplaten)%5C
**Post date:** [June 28, 2021, 8:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F2 "2021-06-28T20:56:09Z")
I’d actually be happy to join this team 🙂
Also pinging @flozi00 @stefan-it in case you guys are interested.
---
**Author:**  [@Dimitre](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDimitre)%5C
**Post date:** [June 28, 2021, 11:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F3 "2021-06-28T23:43:33Z")
Hey @patrickvonplaten if you don’t mind I would like to join the team, I have been looking for an opportunity to get more hands-on experience with audio models, this sounds amazing if you wanna know a little more about my background check out my [GitHub](https://github.com/dimitreOliveira).
---
**Author:**  [@flozi00](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fflozi00)%5C
**Post date:** [June 29, 2021, 7:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F4 "2021-06-29T07:20:58Z")
Hey Patrick,
sounds interesting.
Here is some stuff about more german data [preprocessing/README.md · master · Jaco-Assistant / Scribosermo · GitLab](https://gitlab.com/Jaco-Assistant/Scribosermo/-/blob/master/preprocessing/README.md#datasets)
---
**Author:**  [@birgermoell](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbirgermoell)%5C
**Post date:** [June 29, 2021, 7:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F5 "2021-06-29T07:52:02Z")
I would also like to join this project.
---
**Author:**  [@patrickvonplaten](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpatrickvonplaten)%5C
**Post date:** [June 29, 2021, 2:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F6 "2021-06-29T14:48:04Z")
Awesome, let’s finalize this project! I’ll try to help out here 🙂
---
**Author:**  [@Dimitre](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDimitre)%5C
**Post date:** [June 30, 2021, 1:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F7 "2021-06-30T01:41:26Z")
hey there, I took the liberty to create a channel at discord for this project ([Flax-HuggingFace-Community-Week](https://discord.gg/ABfE9zr5))
---
**Author:**  [@ghofrani](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fghofrani)%5C
**Post date:** [July 7, 2021, 12:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-german%2F7571%2F8 "2021-07-07T12:55:51Z")
Hi guys,
Could you please add me to this team?