Audio Classification
speechbrain
English
lijialudew commited on
Commit
738d959
1 Parent(s): 3a33a3a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -23,16 +23,17 @@ We build a CTC-based phoneme recognition model using wav2vec 2.0 (W2V2) for chil
23
  We show W2V2-MyST-Pro is helpful for improving children's vocalization classification task on two corpus, including [Rapid-ABC](https://openaccess.thecvf.com/content_cvpr_2013/html/Rehg_Decoding_Childrens_Social_2013_CVPR_paper.html) and [BabbleCor](https://osf.io/rz4tx/).
24
 
25
  ## Model Sources
26
- For more information regarding this model, please checkout our paper: (TO-DO)
27
  - **Paper:** https://arxiv.org/pdf/2309.07287.pdf
28
 
29
  ## Model Description
30
 
31
  <!-- Provide a longer summary of what this model is. -->
32
  Folder contains the best checkpoint of the following setting
33
- - **W2V2-MyST by fine-tuning on Librispeech 960h**: save_960h/wav2vec2.ckpt
34
- - **W2V2-Pro trained on phone sequence**: save_MyST_Providence_ep45_filtered/wav2vec2.ckpt
35
- - **W2V2-Pro trained on consonant/vowel sequence**: save_MyST_Providence_ep45_filtered_cv_only/wav2vec2.ckpt
 
36
 
37
  ## Uses
38
  **We develop our complete fine-tuning recipe using SpeechBrain toolkit available at**
 
23
  We show W2V2-MyST-Pro is helpful for improving children's vocalization classification task on two corpus, including [Rapid-ABC](https://openaccess.thecvf.com/content_cvpr_2013/html/Rehg_Decoding_Childrens_Social_2013_CVPR_paper.html) and [BabbleCor](https://osf.io/rz4tx/).
24
 
25
  ## Model Sources
26
+ For more information regarding this model, please checkout our paper:
27
  - **Paper:** https://arxiv.org/pdf/2309.07287.pdf
28
 
29
  ## Model Description
30
 
31
  <!-- Provide a longer summary of what this model is. -->
32
  Folder contains the best checkpoint of the following setting
33
+ - **W2V2-Libri100h**: save_100h/wav2vec2.ckpt
34
+ - **W2V2-MyST**: save_100h_MyST/wav2vec2.ckpt
35
+ - **W2V2-Libri100h-Pro**: save_100h_Providence/wav2vec2.ckpt
36
+ - **W2V2-MyST-Pro**: save_100h_MyST_Providence/wav2vec2.ckpt
37
 
38
  ## Uses
39
  **We develop our complete fine-tuning recipe using SpeechBrain toolkit available at**