speechbrain
/

tts-mstacotron2-libritts

multi-speaker-tts

Model card Files Files and versions Community

speechbrainteam commited on Oct 19, 2023

Commit

ccd38f4

·

1 Parent(s): 61d287c

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -17,7 +17,9 @@ metrics:
 # Text-to-Speech (TTS) with Zero-Shot Multi-Speaker Tacotron2 trained on LibriTTS
-### Note: This project is currently a work in progress. While the model is operational, we are now focusing on enhancing the quality of the generated voice
 This repository provides all the necessary tools for Zero-Shot Multi-Speaker Text-to-Speech (TTS) with SpeechBrain using a variation of [Tacotron2](https://arxiv.org/abs/1712.05884), extended to incorporate speaker identity information when generating speech. It is pretrained on [LibriTTS](https://www.openslr.org/60/).

 # Text-to-Speech (TTS) with Zero-Shot Multi-Speaker Tacotron2 trained on LibriTTS
+**Please Note**: The current model effectively captures speaker identities. Nevertheless, the synthesized speech quality exhibits some metallic characteristics and may include artifacts like overly long pauses.
+We are actively working to enhancing the model and will release updates as soon as improvements are achieved. We warmly welcome contributions from the community to collaboratively make the model even better!
 This repository provides all the necessary tools for Zero-Shot Multi-Speaker Text-to-Speech (TTS) with SpeechBrain using a variation of [Tacotron2](https://arxiv.org/abs/1712.05884), extended to incorporate speaker identity information when generating speech. It is pretrained on [LibriTTS](https://www.openslr.org/60/).