-
I am training VAE and stable audio2 models from scratch, how much will VAE and Diffusion loss reach?My current VAE loss is about 0.4, and diffusion’s mse loss is 0.53.
-
Thanks for making this available!
What are the datasets that you used for modeling training (for the released checkpoints)?
-
**Describe the bug**
In Galician, the "Awards" badges that a user can collect appear in English, the corresponding strings are missing in Pontoon and as such cannot be localized.
**To Reproduce**
…
-
I came across an error when running `generate_data_param.py`, and the `scp` files used in the `simulation_train.yaml` are presented as below:
```
speech_scps:
- /data/tmp/dns5_clean_read_speech_res…
-
**Describe the bug**
Lower buttons on /speak ("skip", "submit",...) aren't visible on smaller screens
**To Reproduce**
Steps to reproduce the behavior:
1. Go to https://commonvoice.mozilla.org/e…
-
Thanks for open-sourcing the code to reproduce the results of the paper.
Which Common Voice Version was used to produce the evaluation/test results? Was it Common Voice 1,2,3 or 4?
-
Sometime the program propose the same record (same phrase, same user) to check, two times no more.
The last happen today around 12:00 (GMT+2) for the phrase "Bilbo e Drago erano entrambi nipoti di Ba…
-
**Describe the bug**
It is reported that there are some wordings that do not go through localization. Please look at the following Discourse post for screenshots:
https://discourse.mozilla.org/t/c…
-
**Describe the bug**
I want to choose the language in sentence collection (write and review)
**To Reproduce**
Steps to reproduce the behavior:
1. Go to https://commonvoice.mozilla.org/fr/write
…
-
See the attached screenshot, whisperX's srt detects the 'SIII' as 'SIIIIIIIIIIIIIIIII…