Hugging Face's logo

flax-community
/
wav2vec2-dhivehi

Automatic Speech Recognition
Transformers
PyTorch
JAX
TensorBoard
Divehi
wav2vec2
pretraining
Inference Endpoints
Model card Files Metrics Community
wav2vec2-dhivehi / README.md
eyna's picture
eyna
add readme
aa7e43b
preview code
|
raw
history blame
1.2 kB
metadata
language: dv
tags:
  - automatic-speech-recognition
datasets:
  - common_voice

Wav2Vec2 Dhivehi

Wav2vec2 pre-pretrained from scratch using common voice dhivehi dataset. The model was trained with Flax during the Flax/Jax Community Week organised by HuggingFace.

Model description

The model used for training is Wav2Vec2 by FacebookAI. It was introduced in the paper "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations" by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli (https://arxiv.org/abs/2006.11477).

This model is available in the 🤗 Model Hub.

Training data

Dhivehi data from Common Voice.

The dataset is also available in the 🤗 Datasets library.

Team members