Commit
•
44871a9
1
Parent(s):
53d03e7
Update README.md
Browse filesadd huggingface tts blog and demo
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
|