Загрузка видео...
Не удалось загрузить видео
🚧 We are working on StyleTTS2 model training. 🏗 I think it's time to show some results from the training... 🔥 The model license is the same as the repo (MIT) 🎙 StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models 🔥... show more
11,532 просмотров • 2 лет назад •via X (Twitter)
Комментарии: 8
Risichad 🦾2 лет назад
Wow, that is also very fast !
Jeff Araujo2 лет назад
Is it possible to fine-tune it using Portuguese language audio?
🍉🍒🍇🍋🧀🍕2 лет назад
can you make it support multilingual like openai tts
mohamed mez2 лет назад
What about Arabic,is it supported?
AI Models | Visit at aimodels.org | Open Source AI2 лет назад
I was looking at StyleTTS2, I was trying to figure out training and inference but it's a bit complicated in the documentation (lots of parts to pull in) I guess I'll have to try the notebook!
Augu8t2 лет назад
How can I display the pets on screen like that?
Py Man2 лет назад
OpenAI voice engine is far better quality
camenduru2 лет назад
OK, MIT license with additional restrictions, but our model's license is MIT.
![Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.](https://image.24vids.com/tw-1672048076469698561/ext_tw_video_thumb/1672047839378300928/pu/img/MuoOBsAyUd-HAI7D.jpg)
