mechanicalsea commited on
Commit
a3109bf
1 Parent(s): 3bd5924

Update README.md

Browse files

add huggingface vc blog and demo.

Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -9,7 +9,7 @@ tags:
9
  - SpeechT5
10
  - Voice Conversion
11
  datasets:
12
- - CMU ARCTIC
13
  - bdl
14
  - clb
15
  - rms
@@ -22,6 +22,10 @@ datasets:
22
 
23
  This manifest is an attempt to recreate the Voice Conversion recipe used for training [SpeechT5](https://aclanthology.org/2022.acl-long.393). This manifest was constructed using [CMU ARCTIC](http://www.festvox.org/cmu_arctic/) four speakers, e.g., bdl, clb, rms, slt. There are 932 utterances for training, 100 utterances for validation, and 100 utterance for evaluation.
24
 
 
 
 
 
25
  ### Requirements
26
 
27
  - [SpeechBrain](https://github.com/speechbrain/speechbrain) for extracting speaker embedding
@@ -50,4 +54,4 @@ If you find our work is useful in your research, please cite the following paper
50
  year = {2022},
51
  pages={5723--5738},
52
  }
53
- ```
 
9
  - SpeechT5
10
  - Voice Conversion
11
  datasets:
12
+ - CMUARCTIC
13
  - bdl
14
  - clb
15
  - rms
 
22
 
23
  This manifest is an attempt to recreate the Voice Conversion recipe used for training [SpeechT5](https://aclanthology.org/2022.acl-long.393). This manifest was constructed using [CMU ARCTIC](http://www.festvox.org/cmu_arctic/) four speakers, e.g., bdl, clb, rms, slt. There are 932 utterances for training, 100 utterances for validation, and 100 utterance for evaluation.
24
 
25
+ ### News
26
+
27
+ - 8 February 2023: SpeechT5 is integrated as an official model into the Hugging Face Transformers library [[Blog](https://huggingface.co/blog/speecht5)] and [[Demo](https://huggingface.co/spaces/Matthijs/speecht5-vc-demo)].
28
+
29
  ### Requirements
30
 
31
  - [SpeechBrain](https://github.com/speechbrain/speechbrain) for extracting speaker embedding
 
54
  year = {2022},
55
  pages={5723--5738},
56
  }
57
+ ```