patrickvonplaten
commited on
Commit
•
f3dce52
1
Parent(s):
0019381
Update README.md
Browse files
README.md
CHANGED
@@ -31,6 +31,13 @@ For more information, please refer to Section *5.1.2* of the [official XLS-R pap
|
|
31 |
|
32 |
## Usage
|
33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
As this a standard sequence to sequence transformer model, you can use the `generate` method to generate the
|
35 |
transcripts by passing the speech features to the model.
|
36 |
|
@@ -72,3 +79,9 @@ See the row of **XLS-R (0.3B)** for the performance on [Covost2](https://hugging
|
|
72 |
|
73 |
![results image](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/X-%3EEnglish.png)
|
74 |
|
|
|
|
|
|
|
|
|
|
|
|
31 |
|
32 |
## Usage
|
33 |
|
34 |
+
### Demo
|
35 |
+
|
36 |
+
The model can be tested directly on the speech recognition widget on this model card!
|
37 |
+
Simple record some audio in one of the possible spoken languages or pick an example audio file to see how well the checkpoint can translate the input.
|
38 |
+
|
39 |
+
### Example
|
40 |
+
|
41 |
As this a standard sequence to sequence transformer model, you can use the `generate` method to generate the
|
42 |
transcripts by passing the speech features to the model.
|
43 |
|
79 |
|
80 |
![results image](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/X-%3EEnglish.png)
|
81 |
|
82 |
+
## More XLS-R models for `{lang}` -> `en` Speech Translation
|
83 |
+
|
84 |
+
- [Wav2Vec2-XLS-R-300M-21-EN](https://huggingface.co/facebook/wav2vec2-xls-r-300m-21-to-en)
|
85 |
+
- [Wav2Vec2-XLS-R-1B-21-EN](https://huggingface.co/facebook/wav2vec2-xls-r-1b-21-to-en)
|
86 |
+
- [Wav2Vec2-XLS-R-2B-21-EN](https://huggingface.co/facebook/wav2vec2-xls-r-2b-21-to-en)
|
87 |
+
- [Wav2Vec2-XLS-R-2B-22-16](https://huggingface.co/facebook/wav2vec2-xls-r-2b-22-to-16)
|