add readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: dv
|
| 3 |
+
tags:
|
| 4 |
+
- automatic-speech-recognition
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Wav2Vec2 Dhivehi
|
| 10 |
+
|
| 11 |
+
Wav2vec2 pre-pretrained from scratch using common voice dhivehi dataset. The model was trained with Flax during the [Flax/Jax Community Week](https://discss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104) organised by HuggingFace.
|
| 12 |
+
|
| 13 |
+
## Model description
|
| 14 |
+
|
| 15 |
+
The model used for training is [Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) by FacebookAI. It was introduced in the paper
|
| 16 |
+
"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).
|
| 17 |
+
|
| 18 |
+
This model is available in the 🤗 [Model Hub](https://huggingface.co/facebook/wav2vec2-base-960h).
|
| 19 |
+
|
| 20 |
+
## Training data
|
| 21 |
+
|
| 22 |
+
Dhivehi data from [Common Voice](https://commonvoice.mozilla.org/en/datasets).
|
| 23 |
+
|
| 24 |
+
The dataset is also available in the 🤗 [Datasets](https://huggingface.co/datasets/common_voice) library.
|
| 25 |
+
|
| 26 |
+
## Team members
|
| 27 |
+
|
| 28 |
+
- Shahu Kareem ([@shahukareem](https://huggingface.co/shahukareem))
|
| 29 |
+
- Eyna ([@eyna](https://huggingface.co/eyna))
|