-
Hi,
Apologies if this is a silly question. If I train a model with a dataset made from a different Sample rate; will this technique still work? eg the training data would come from normal speech/si…
-
Hi,
How dominant speaker concept concept implemented in Skype media bot SDK? How it works and Use that in the application to recorded successful audio and video from media stream?
Who is the firs…
-
Have you try this on multi-speaker way ?
-
# Task Name
African American Vernacular English (AAVE) Speech Recognition
## Task Objective
Mainstream speech recognition systems often perform poorly on non-standard dialects and sociolects,…
-
빠른 TTS를 위한 좋은 논문을 내주셔서 감사합니다.
제목에 해당하는 부분을 먼저 말씀드리자면,
(944525a commit) train.py의 127번째 line 에서
logger.info에서 진행도를 계산하는 부분에서 gpu 개수가 고려가 되어 있지 않습니다.
해당 부분:
logger.info('Train Epoch: {} [{}/…
Sejik updated
3 years ago
-
I'm a native speaker of Hungarian, and someone who translates internet content into Hungarian as a hobby, and I noticed that there are several major issues with the translation of this document, that …
-
### Description
When using the `poetry init` command to create a new project, the interactive dependency addition step fails to find packages (e.g., `numpy`). However, the poetry add command works as…
-
hello
When testing my dataset
In metadata_to_text.py script, I saw the error message
that Column(s) ['gender'] do not exist"
I don't have `gender` and` speaker_id` in my dataset.
Do I need both…
-
We are excited to announce the planning phase for the JAVAFEST community-driven conference organized by the Bangalore Java User Group. To make this year's event even more successful, we need your idea…
-
Hi,
I am attempting zero-shot voice conversion by using only a few audio sentences of a target speaker. I am training a speaker embedding for this speaker using the make_spect.py and make_metadata.py…