Commit
•
8ad67c6
1
Parent(s):
529e458
Fixed readme
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ Wav2Vec2 is a pretrained model for Automatic Speech Recognition (ASR) and was re
|
|
| 25 |
|
| 26 |
Similar to Wav2Vec2, XLSR-Wav2Vec2 learns powerful speech representations from hundreds of thousands of hours of speech in more than 50 languages of unlabeled speech. Similar, to BERT's masked language modeling, the model learns contextualized speech representations by randomly masking feature vectors before passing them to a transformer network.
|
| 27 |
|
| 28 |
-
This model was trained on Greek CommonVoice speech data (364MB) for
|
| 29 |
|
| 30 |
### How to use for inference:
|
| 31 |
|
|
|
|
| 25 |
|
| 26 |
Similar to Wav2Vec2, XLSR-Wav2Vec2 learns powerful speech representations from hundreds of thousands of hours of speech in more than 50 languages of unlabeled speech. Similar, to BERT's masked language modeling, the model learns contextualized speech representations by randomly masking feature vectors before passing them to a transformer network.
|
| 27 |
|
| 28 |
+
This model was trained on Greek CommonVoice speech data (364MB) for 60 epochs on a single NVIDIA RTX 3080, for aprox. 8hrs.
|
| 29 |
|
| 30 |
### How to use for inference:
|
| 31 |
|