Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,16 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
datasets:
|
4 |
+
- librispeech_asr
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
library_name: transformers
|
10 |
---
|
11 |
+
# Wav2Vec2 XLS-R-300m Finetuning using 1hr of Librispeech
|
12 |
+
XLS-R 300m pretrained model found [here](https://huggingface.co/facebook/wav2vec2-xls-r-300m) is finetuned using 1hr of LibriSpeech Train-Clean-100 subset sampled at random.
|
13 |
+
|
14 |
+
**[XLS-R paper](https://arxiv.org/abs/2111.09296)**
|
15 |
+
|
16 |
+
Training Code is available on [this colab notebook](). (The notebook is inspired by [this notebook](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLS_R_on_Common_Voice.ipynb))
|