mechanicalsea commited on
Commit
44871a9
1 Parent(s): 53d03e7

Update README.md

Browse files

add huggingface tts blog and demo

Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -19,6 +19,10 @@ pipeline_tag: text-to-speech
19
 
20
  This manifest is an attempt to recreate the Text-to-Speech recipe used for training [SpeechT5](https://aclanthology.org/2022.acl-long.393). This manifest was constructed using [LibriTTS](http://www.openslr.org/60/) clean datasets, including train-clean-100 and train-clean-360 for training, dev-clean for validation, and test-clean for evaluation. The test-clean-200 contains 200 utterances id for the mean option score (MOS), and the comparison mean option score (CMOS).
21
 
 
 
 
 
22
  ### Requirements
23
 
24
  - [SpeechBrain](https://github.com/speechbrain/speechbrain) for extracting speaker embedding
 
19
 
20
  This manifest is an attempt to recreate the Text-to-Speech recipe used for training [SpeechT5](https://aclanthology.org/2022.acl-long.393). This manifest was constructed using [LibriTTS](http://www.openslr.org/60/) clean datasets, including train-clean-100 and train-clean-360 for training, dev-clean for validation, and test-clean for evaluation. The test-clean-200 contains 200 utterances id for the mean option score (MOS), and the comparison mean option score (CMOS).
21
 
22
+ ### News
23
+
24
+ - 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-tts-demo)].
25
+
26
  ### Requirements
27
 
28
  - [SpeechBrain](https://github.com/speechbrain/speechbrain) for extracting speaker embedding