harmlessman
harmlessman
I tried that method before, but it was possible to execute `mecab`. However, I did not choose this method because the installation process was very cumbersome. (And the same error...
@erogol I will refer to it when testing source on Linux :).
I made a cross-platform G2p for Korean! I will upload a phonemizer with g2p with `test_korean_phonemizer.py` soon. :)
I'm done!
The above articles seem to be the code before pull today. Is it a review of the codes before I pull?
There are no words in the code posted today on dictionary.py that have been corrected, and 'TTS/ts/utils/text/korean/korean.py' The function get_mode of also does not exist. The codes you kindly reviewed...
I still haven’t found a way to improve the latency issue. There are many forked repositories out there, but most of them show similar performance in terms of speed. The...
When I ran the inference code on a GCP instance with a T4 GPU, it took around 5 seconds to generate speech for a typical-length sentence. This time measurement only...
Thank you for your response. I’ve taken a look at the repository you shared. It seems that chatterbox-streaming is used to enable faster first-audio generation via streaming, which is impressive....
Hi, @jjmlovesgit Here are the results I got when testing chatterbox-streaming for audio generation: ``` text = "Welcome to the world of streaming text-to-speech! This audio will be generated and...