mariagrandury
commited on
Commit
•
2e6a6e4
1
Parent(s):
69128c5
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: es
|
3 |
+
tags:
|
4 |
+
- audio
|
5 |
+
- automatic-speech-recognition
|
6 |
+
datasets:
|
7 |
+
- common_voice
|
8 |
+
---
|
9 |
+
|
10 |
+
# Wav2Vec2 Spanish
|
11 |
+
|
12 |
+
Spanish Wav2Vec2 model pre-trained using the Spanish portion of the Common Voice dataset during the [Flax x Hugging Face](https://discss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104) community event.
|
13 |
+
|
14 |
+
Team:
|
15 |
+
[@mariagrandury](https://github.com/mariagrandury),
|
16 |
+
[@mrm8488](https://github.com/mrm8488),
|
17 |
+
[@edugp](https://github.com/edugp) and
|
18 |
+
[@pcuenq](https://github.com/pcuenq).
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
The model used for training is [Wav2Vec2] by FacebookAI. It was introduced in the paper
|
23 |
+
"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).
|
24 |
+
|
25 |
+
This model is available in the 🤗 [Model Hub](https://huggingface.co/facebook/wav2vec2-base-960h).
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
### How to use
|
30 |
+
|
31 |
+
### Limitations and bias
|
32 |
+
|
33 |
+
## Training data
|
34 |
+
|
35 |
+
Spanish portion of [Common Voice](https://commonvoice.mozilla.org/en/datasets). Common Voice is an open source, multi-language dataset of voices part of Mozilla's initiative to help teach machines how real people speak.
|
36 |
+
|
37 |
+
The dataset is also available in the 🤗 [Datasets](https://huggingface.co/datasets/common_voice) library.
|
38 |
+
|
39 |
+
### Training procedure
|
40 |
+
|
41 |
+
### Eval results
|