-
看了你们其他的文章,有介绍将DAC提的token用来训unicats ,但是dac这样的token有8组每组1024个,但是unicat输入的事单一一组token,这个怎么转换呢?或者是有新的其他架构?
-
Hi @cantabile-kwok ,
I have also implemented UniCATS's vec2wav but that model is too slow, so I am curious to know the inference speed of this model. Actually, I am interested in integrating CTX-vec2…
-
Hi @cantabile-kwok, I’ve been chipping away on the unofficial implementation of the UniCATS paper [here](https://github.com/francislata/unicats). Since the second part is out and it sounds like you’re…
-
-
Hi @cantabile-kwok, in the paper, there was not any recommended text or phoneme tokenizer to use. Do you have recommendations of what to use?
Thank you.
-
Hello @cantabile-kwok ! Thanks for this amazing project and congratulations on acceptance in AAAI.
I have a question. What vq-wav2vec checkpoint was used for tokenizing the speech data?
I'm reprod…
-
I did not find the paper about this project, but since it is AR LLM based tts, I want to know the idea in the fish-speech that superior to privious works like TorToise and Cosyvoice. Is there and inst…
-
-
Congratulations on acceptance in AAAI.
I have some questions about your training method.
1. From reading other papers that use similar techniques, some of these have trained models on huge datas…
-
README 中说明采用 16000 采样率,但是在 demo 页面 https://cpdu.github.io/unicats/ 中的音频是 24000 的采样率,这是什么原因呢?