There is currently only a multilingually pretrained model for Persian Wav2Vec2. Let’s make a Wav2Vec2 only pretrained on Persian.
A randomly initialized Wav2Vec2 model
FlaxWav2Vec2 will be merged soon: [Flax] Add wav2vec2 by Patrickvonplaten · Pull Request #12271 · huggingface/transformers · GitHub and a pretraining script should be relatively easy to be merged.
The best Persian ASR model.
It might make sense to use more data than just the common voice.