Audio-to-Audio
PyTorch
Safetensors
lucadellalib commited on
Commit
e0ffa47
·
verified ·
1 Parent(s): cf1dce9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -3
README.md CHANGED
@@ -1,3 +1,49 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model:
4
+ - microsoft/wavlm-large
5
+ pipeline_tag: audio-to-audio
6
+ datasets:
7
+ - mythicinfinity/libritts
8
+ ---
9
+
10
+ # FocalCodec
11
+
12
+ A low-bitrate single-codebook 16 kHz speech codec based on [focal modulation](https://arxiv.org/abs/2203.11926).
13
+
14
+ This repository contains the **25 Hz checkpoint** trained on **LibriTTS 960**, as described in the preprint.
15
+
16
+ - 📜 **Preprint**: https://arxiv.org/abs/2502.04465
17
+
18
+ - 🌐 **Project Page**: https://lucadellalib.github.io/focalcodec-web/
19
+
20
+ - 💾 **GitHub**: https://github.com/lucadellalib/focalcodec
21
+
22
+ <img src="focalcodec.png" width="700">
23
+
24
+ ---------------------------------------------------------------------------------------------------------
25
+
26
+ ## ▶️ Quickstart
27
+
28
+ See the readme at: https://github.com/lucadellalib/focalcodec
29
+
30
+ ---------------------------------------------------------------------------------------------------------
31
+
32
+ ## @ Citing
33
+
34
+ ```
35
+ @article{dellalibera2025focalcodec,
36
+ title = {{FocalCodec}: Low-Bitrate Speech Coding via Focal Modulation Networks},
37
+ author = {Luca {Della Libera} and Francesco Paissan and Cem Subakan and Mirco Ravanelli},
38
+ journal = {arXiv preprint arXiv:2502.04465},
39
+ year = {2025},
40
+ }
41
+ ```
42
+
43
+ ---------------------------------------------------------------------------------------------------------
44
+
45
+ ## 📧 Contact
46
+
47
48
+
49
+ ---------------------------------------------------------------------------------------------------------