leonardvorbeck
commited on
Commit
•
3c9ddc6
1
Parent(s):
8a277b8
Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,9 @@ datasets:
|
|
7 |
- fisher
|
8 |
tags:
|
9 |
- speech
|
10 |
-
-
|
|
|
|
|
11 |
- wav2vec2
|
12 |
license: apache-2.0
|
13 |
---
|
@@ -23,7 +25,8 @@ Speech datasets from multiple domains were used to pretrain the model:
|
|
23 |
- [Switchboard](https://catalog.ldc.upenn.edu/LDC97S62): telephone speech corpus; noisy telephone data
|
24 |
- [Fisher](https://catalog.ldc.upenn.edu/LDC2004T19): conversational telephone speech; noisy telephone data
|
25 |
|
26 |
-
When using the model make sure that your speech input is also sampled at 16Khz.
|
|
|
27 |
|
28 |
[Paper Robust Wav2Vec2](https://arxiv.org/abs/2104.01027)
|
29 |
|
7 |
- fisher
|
8 |
tags:
|
9 |
- speech
|
10 |
+
- automatic-speech-recognition
|
11 |
+
- CTC
|
12 |
+
- Attention
|
13 |
- wav2vec2
|
14 |
license: apache-2.0
|
15 |
---
|
25 |
- [Switchboard](https://catalog.ldc.upenn.edu/LDC97S62): telephone speech corpus; noisy telephone data
|
26 |
- [Fisher](https://catalog.ldc.upenn.edu/LDC2004T19): conversational telephone speech; noisy telephone data
|
27 |
|
28 |
+
When using the model make sure that your speech input is also sampled at 16Khz.
|
29 |
+
Check out [this blog](https://huggingface.co/blog/fine-tune-wav2vec2-english) for more information.
|
30 |
|
31 |
[Paper Robust Wav2Vec2](https://arxiv.org/abs/2104.01027)
|
32 |
|