Hugging Face's logo

mispeech
/
dashengtokenizer

Audio-to-Audio
Transformers
Safetensors
dashengtokenizer
feature-extraction
audio-classification
signal-processing
custom_code
Model card Files
xet
Community
Heinrich Dinkel commited on
Commit
2dfe0e8
·
1 Parent(s): ae36747

updated readme

Browse files
Files changed (1) hide show
  1. README.md +5 -7
README.md CHANGED
@@ -15,13 +15,6 @@ Compared to previous works, our framework simply trains a single linear layer to
15
 
16
  ![Framework](./figures/framework.png)
17
 
18
-
19
- # Results
20
-
21
- ![Audio Generation Results](./figures/audio_generation_results.png)
22
- ![Audio Understanding Results](./figures/audio_understanding_results.png)
23
-
24
-
25
  ## Usage
26
 
27
  ### Installation
@@ -87,6 +80,11 @@ features = model.encode(audio)
87
 
88
  - Optimized for 16kHz mono audio
89
 
 
 
 
 
 
90
  ## Citation
91
 
92
  If you use DashengTokenizer in your research, please cite:
 
15
 
16
  ![Framework](./figures/framework.png)
17
 
 
 
 
 
 
 
 
18
  ## Usage
19
 
20
  ### Installation
 
80
 
81
  - Optimized for 16kHz mono audio
82
 
83
+ ## Results
84
+
85
+ ![Audio Generation Results](./figures/audio_generation_results.png)
86
+ ![Audio Understanding Results](./figures/audio_understanding_results.png)
87
+
88
  ## Citation
89
 
90
  If you use DashengTokenizer in your research, please cite: