patrickvonplaten
commited on
Commit
•
bd5c278
1
Parent(s):
6a1a5e1
correct readme
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ license: cc-by-nc-4.0
|
|
9 |
|
10 |
# Wav2Vec2-Large-VoxPopuli
|
11 |
|
12 |
-
[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) large model pretrained on the
|
13 |
|
14 |
**Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
|
15 |
Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*
|
@@ -17,3 +17,8 @@ Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/210
|
|
17 |
**Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*
|
18 |
|
19 |
See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/)
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
# Wav2Vec2-Large-VoxPopuli
|
11 |
|
12 |
+
[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) large model pretrained on the it unlabeled subset of [VoxPopuli corpus](https://arxiv.org/abs/2101.00390).
|
13 |
|
14 |
**Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
|
15 |
Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*
|
|
|
17 |
**Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*
|
18 |
|
19 |
See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/)
|
20 |
+
|
21 |
+
# Fine-Tuning
|
22 |
+
|
23 |
+
Please refer to [this blog](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) on how to fine-tune this model on a specific language. Note that you should replace `"facebook/wav2vec2-large-xlsr-53"` with this checkpoint for fine-tuning.
|
24 |
+
|