dragonSwing
commited on
Commit
•
5acb7ff
1
Parent(s):
e0ac1cb
Update README.md
Browse files
README.md
CHANGED
@@ -56,7 +56,7 @@ Please refer to [huggingface blog](https://huggingface.co/blog/fine-tune-wav2vec
|
|
56 |
|without LM| 8.41 | 17.82 |
|
57 |
|with 4-grams LM| 4.04 | 9.66 |
|
58 |
|
59 |
-
The language model was trained using [
|
60 |
|
61 |
### Install SpeechBrain
|
62 |
To use this model, you should install speechbrain from source. This is not required for speechbrain version > 0.5.10
|
|
|
56 |
|without LM| 8.41 | 17.82 |
|
57 |
|with 4-grams LM| 4.04 | 9.66 |
|
58 |
|
59 |
+
The language model was trained using [OSCAR](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109) dataset on about 32GB of crawled text.
|
60 |
|
61 |
### Install SpeechBrain
|
62 |
To use this model, you should install speechbrain from source. This is not required for speechbrain version > 0.5.10
|