novateur commited on
Commit
9789e02
β€’
1 Parent(s): adf8c68

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -8,18 +8,17 @@ tags:
8
  - tokenizer
9
  - codec-representation
10
  ---
11
- # WavTokenizer
12
- SOTA Discrete Codec Models With Forty Tokens Per Second for Audio Language Modeling
13
 
14
 
15
 
16
  [![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://github.com/jishengpeng/wavtokenizer)
17
  [![demo](https://img.shields.io/badge/WanTokenizer-Demo-red)](https://wavtokenizer.github.io/)
18
- [![model](https://img.shields.io/badge/%F0%9F%A4%97%20WavTokenizer-Models-blue)](https://github.com/jishengpeng/wavtokenizer)
19
 
20
 
21
 
22
- ### πŸŽ‰πŸŽ‰ with WavTokenizer, you can represent speech, music, and audio with only 40 tokens one second!
23
  ### πŸŽ‰πŸŽ‰ with WavTokenizer, You can get strong reconstruction results.
24
  ### πŸŽ‰πŸŽ‰ WavTokenizer owns rich semantic information and is build for audio language models such as GPT4-o.
25
 
@@ -110,8 +109,8 @@ audio_out = wavtokenizer.decode(features, bandwidth_id=bandwidth_id)
110
 
111
  | Model name | HuggingFace | Corpus | aa | Parameters | Open-Source |
112
  |:--------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:---------:|:----------:|:------:|
113
- | WavTokenizer-small-600-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | LibriTTS | 40 | Speech | √ |
114
- | WavTokenizer-small-320-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | LibriTTS | 75 | Speech | √|
115
  | WavTokenizer-medium-600-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | 10000 Hours | 40 | Speech, Audio, Music | Coming Soon|
116
  | WavTokenizer-medium-320-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | 10000 Hours | 75 | Speech, Audio, Music | Coming Soon|
117
  | WavTokenizer-large-600-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | LibriTTS | 40 | Speech, Audio, Music | Coming Soon|
 
8
  - tokenizer
9
  - codec-representation
10
  ---
11
+ # WavTokenizer: SOTA Discrete Codec Models With Forty Tokens Per Second for Audio Language Modeling
 
12
 
13
 
14
 
15
  [![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://github.com/jishengpeng/wavtokenizer)
16
  [![demo](https://img.shields.io/badge/WanTokenizer-Demo-red)](https://wavtokenizer.github.io/)
17
+ [![model](https://img.shields.io/badge/%F0%9F%A4%97%20WavTokenizer-Models-blue)](https://huggingface.co/novateur/WavTokenizer)
18
 
19
 
20
 
21
+ ### πŸŽ‰πŸŽ‰ with WavTokenizer, you can represent speech, music, and audio with only 40 tokens per second!
22
  ### πŸŽ‰πŸŽ‰ with WavTokenizer, You can get strong reconstruction results.
23
  ### πŸŽ‰πŸŽ‰ WavTokenizer owns rich semantic information and is build for audio language models such as GPT4-o.
24
 
 
109
 
110
  | Model name | HuggingFace | Corpus | aa | Parameters | Open-Source |
111
  |:--------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:---------:|:----------:|:------:|
112
+ | WavTokenizer-small-600-24k-4096 | [πŸ€—](https://huggingface.co/novateur/WavTokenizer/blob/main/WavTokenizer_small_600_24k_4096.ckpt) | LibriTTS | 40 | Speech | √ |
113
+ | WavTokenizer-small-320-24k-4096 | [πŸ€—](https://huggingface.co/novateur/WavTokenizer/blob/main/WavTokenizer_small_320_24k_4096.ckpt) | LibriTTS | 75 | Speech | √|
114
  | WavTokenizer-medium-600-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | 10000 Hours | 40 | Speech, Audio, Music | Coming Soon|
115
  | WavTokenizer-medium-320-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | 10000 Hours | 75 | Speech, Audio, Music | Coming Soon|
116
  | WavTokenizer-large-600-24k-4096 | [πŸ€—](https://github.com/jishengpeng/wavtokenizer) | LibriTTS | 40 | Speech, Audio, Music | Coming Soon|