• https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.

    XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG

  • Joined on 2022-10-10
ecker pushed to main at ecker/tortoise-tts 2023-02-08 14:14:48 +00:00
d9a9fa6a82 Added two flags/settings: embed output settings, slimmer computed voice latents
ecker commented on issue ecker/tortoise-tts#9 2023-02-07 21:45:53 +00:00
Keeping gradio from phoning home

Added in commit f03b6b8d977b22e5747a81e58d31607dae4ffe9d, courtesy of >>>/g/89228409

ecker pushed to main at ecker/tortoise-tts 2023-02-07 21:44:40 +00:00
f03b6b8d97 disable telemetry/what-have-you if not requesting a public Gradio URL
ecker commented on pull request ecker/tortoise-tts#7 2023-02-07 21:09:49 +00:00
Fixed spelling error in api.format_conditioning

Already ahead of you, just didn't push the fix in time.

ecker pushed to main at ecker/tortoise-tts 2023-02-07 21:09:03 +00:00
479f30c808 Merge pull request 'Added convert.sh' (#8) from lightmare/tortoise-tts:convert_sh into main
40f52fa8d1 Added convert.sh
Compare 2 commits »
ecker merged pull request ecker/tortoise-tts#8 2023-02-07 21:09:02 +00:00
Added convert.sh
ecker reopened pull request ecker/tortoise-tts#8 2023-02-07 21:07:40 +00:00
Added convert.sh
ecker created branch main in ecker/tortoise-tts 2023-02-07 21:06:20 +00:00
ecker deleted branch master from ecker/tortoise-tts 2023-02-07 21:06:19 +00:00
ecker deleted branch main from ecker/tortoise-tts 2023-02-07 21:02:37 +00:00
ecker closed pull request ecker/tortoise-tts#7 2023-02-07 21:02:36 +00:00
Fixed spelling error in api.format_conditioning
ecker closed pull request ecker/tortoise-tts#8 2023-02-07 21:02:36 +00:00
Added convert.sh
ecker created branch master in ecker/tortoise-tts 2023-02-07 20:58:55 +00:00
ecker pushed to master at ecker/tortoise-tts 2023-02-07 20:58:55 +00:00
ecker pushed to main at ecker/tortoise-tts 2023-02-07 20:56:14 +00:00
6ebdde58f0 (finally) added the CVVP model weigh slider, latents export more data too for weighing against CVVP
ecker pushed to main at ecker/tortoise-tts 2023-02-07 18:35:46 +00:00
793515772a un-hardcoded input output sampling rates (changing them "works" but leads to wrong audio, naturally)
ecker pushed to main at ecker/tortoise-tts 2023-02-07 13:51:11 +00:00
5f934c5feb (maybe) fixed an issue with using prompt redactions (emotions) on CPU causing a crash, because for some reason the wav2vec_alignment assumed CUDA was always available
ecker commented on issue ecker/tortoise-tts#6 2023-02-07 13:50:10 +00:00
emotions not working with CPU

Should be fixed in commit ab3864563dd2a46a8fcbbd2bd39e4a523f587504. I say should, because, while I did force TorToiSe to use my CPU, I'm not sure how guaranteed it was, even with compute time…

ecker pushed to main at ecker/tortoise-tts 2023-02-07 13:46:43 +00:00
ab3864563d (maybe) fixed an issue with using prompt redactions (emotions) on CPU causing a crash, because for some reason the wav2vec_alignment assumed CUDA was always available
ecker closed issue ecker/tortoise-tts#5 2023-02-07 05:24:23 +00:00
In line 176 of app.py, I found it's very helpful to sort the voices in gradio as it can become quite difficult to find things otherwise