-
Investigate if it is worthwhile to replace `tools.logging` with [Timbre](https://github.com/taoensso/timbre?tab=readme-ov-file). Although Timbre can function as a backend for `tools.logging`, it does…
-
# Task Name
Music instrument timbre transfer
## Task Objective
Timbre transfer is a music editing technique that aims to convert the sound produced by one instrument so that it resembles the …
-
您好,请问 FAcodec/modules /quantize.py中FApredictors中forward_v2函数注释掉了
`spk_pred = self.timbre_predictor(timbre)[0]`
这行代码,因此timbre为None,这里会导致后面
```
spk_pred_logits = preds['timbre']
spk_loss …
-
I noticed that when synthesizing different sentences, the voice timbre sounds inconsistent, as if it comes from different people, even though it’s supposed to be the same voice. How can this issue be …
-
Hi,
I found your work is interesting, would it be possible to release the data used for the timbre transfer task?
Thank you in advance.
-
Hi! Nice work!
Could you share how many steps would be sufficient to train a new model? I'm trying to train a 16k FAcodec. The results reconstructed by ckpt 130,000 still sound different from the rea…
-
Hi, all
I see no benefit from the CLVP module, the best score AR generated mel code may not so good, even with some timbre mixture, Should we put the speaker cond into the text tokens during tr…
-
Hi there!
What would you think of perhaps having a unit test in Timbre's core for `slf4j-timbre`? Might be a good way to help ensure that I don't accidentally break anything on your side when relea…
-
Coirault/Laforte :
- Sous l’appellation « Titre/référence de l’air/timbre » : regrouper Timbre de l’air + Timbre référencé
-
My understanding is that the timbre conversion of this project is a model trained in advance, which can only convert a timbre, instead of providing an audio, it can extract the timbre and clone it, ri…