Update README.md

#2
by reach-vb HF staff - opened
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -9,7 +9,7 @@ We introduce AudioSeal, a method for speech localized watermarking, with state-o
9
  Audioseal achieves state-of-the-art detection performance of both natural and synthetic speech at the sample level (1/16k second resolution), it generates limited alteration of signal quality and is robust to many types of audio editing.
10
  Audioseal is designed with a fast, single-pass detector, that significantly surpasses existing models in speed — achieving detection up to two orders of magnitude faster, making it ideal for large-scale and real-time applications.
11
 
12
- # :mate: Installation
13
 
14
  AudioSeal requires Python >=3.8, Pytorch >= 1.13.0, [omegaconf](https://omegaconf.readthedocs.io/), [julius](https://pypi.org/project/julius/), and numpy. To install from PyPI:
15
 
@@ -25,7 +25,7 @@ cd audioseal
25
  pip install -e .
26
  ```
27
 
28
- # :gear: Models
29
 
30
  We provide the checkpoints for the following models:
31
 
@@ -40,7 +40,7 @@ Note that the message is optional and has no influence on the detection output.
40
 
41
  **Note**: We are working to release the training code for anyone wants to build their own watermarker. Stay tuned !
42
 
43
- # :abacus: Usage
44
 
45
  Audioseal provides a simple API to watermark and detect the watermarks from an audio sample. Example usage:
46
 
 
9
  Audioseal achieves state-of-the-art detection performance of both natural and synthetic speech at the sample level (1/16k second resolution), it generates limited alteration of signal quality and is robust to many types of audio editing.
10
  Audioseal is designed with a fast, single-pass detector, that significantly surpasses existing models in speed — achieving detection up to two orders of magnitude faster, making it ideal for large-scale and real-time applications.
11
 
12
+ # 🧉 Installation
13
 
14
  AudioSeal requires Python >=3.8, Pytorch >= 1.13.0, [omegaconf](https://omegaconf.readthedocs.io/), [julius](https://pypi.org/project/julius/), and numpy. To install from PyPI:
15
 
 
25
  pip install -e .
26
  ```
27
 
28
+ # ⚙️ Models
29
 
30
  We provide the checkpoints for the following models:
31
 
 
40
 
41
  **Note**: We are working to release the training code for anyone wants to build their own watermarker. Stay tuned !
42
 
43
+ # 🧮 Usage
44
 
45
  Audioseal provides a simple API to watermark and detect the watermarks from an audio sample. Example usage:
46