---
license: apache-2.0
language:
- yue
library_name: transformers
---

# Cantonese Wav2Vec2-Conformer-Base with Relative Position Embeddings

wav2vec 2.0 Conformer with relative position embeddings, pretrained on 
2.8K hours of Cantonese spontaneous speech data sampled at 16kHz.

Note: This model has not been fine-tuned on labeled text data.


## Alternative Version

An alternative version of the model which was pre-trained on the same dataset but
with setting `layer_norm_first` to `false` is available [here](https://drive.google.com/file/d/1rbP-6pZfR5ieqAwd5_X2KzipLuKpXSsQ/view?usp=sharing)
as a fairseq checkpoint and may give better downstream results.


## Citation

Please cite the following paper if you use the model.

```
@inproceedings{rcfhuang23_interspeech,
	author     = {Ranzo C. F. Huang and Brian Mak},
	year       = {2023},
	title      = {{wav2vec 2.0 ASR} for {Cantonese}-Speaking Older Adults in a Clinical Setting},
	booktitle  = {Interspeech 2023},
	pubstate   = {forthcoming},
}
```