-
-
-
-
-
-
We are currently exploring Text-to-Speech (TTS) models to identify an optimal solution for our project. Our primary requirements are as follows:
1. **Fine-Tuning Capability or Voice Cloning**: The …
t4r7k updated
9 months ago
-
Running `cmake -DCMAKE_INSTALL_PREFIX=$HOME/local .. && make install` gives me:
```
-- Setting installation directory...
-- Include: /home/ivan/local/include
-- Lib: /home/ivan/local/lib…
-
Which new datasets should we offer and prioritize in torchaudio?
I want to follow-up on #31 and a few of the recent PRs. Instead of aiming to have an exhaustive list of datasets, we should focus on…
-
Thank you very much for all your help and support.
I want to train with original data in a speech seperation task, but the samples in the egs2 folder use a specific dataset (WHAM!, WSJ1, etc.).
Ho…
-
The following DCRs suggest several changes that are somewhat related to each other, which is the reason they are listed together. These are mostly based on existing samples [Sample #30](https://githu…