ben_mkiv
  • Joined on 2023-08-16
ben_mkiv commented on issue ecker/ai-voice-cloning#349 2023-08-26 15:50:33 +00:00
unload_tts() doesnt unload the voice model from video memory

i tried to find the root of the problem, but haven't succeed yet. thought you might have an idea.

is run_training() maybe already called on another thread/process and therefor not able to…

ben_mkiv created pull request ecker/ai-voice-cloning#350 2023-08-26 15:46:43 +00:00
Websocket fixes / additions
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-26 15:44:18 +00:00
b72f2216bf added websocket server arguments to enabled it (now disabled by default) and to specify the address/port to listen on
6f0f148782 websocket server: fix for model loading (just overriding args didn't do it after all...)
b4dc103931 I don't know how I did not commit the 'sample from the voices to construct the input prompt for vall-e' change but this helps
a657623cbc updated vall-e training template to use path-based speakers because it would just have a batch/epoch size of 1 otherwise; revert hardcoded 'spit processed dataset to this path' from my training rig to spit it out in a sane spot
Compare 14 commits »
ben_mkiv opened issue ecker/ai-voice-cloning#349 2023-08-26 14:46:52 +00:00
unload_tts() doesnt unload the voice model from video memory
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-25 23:41:40 +00:00
578a5bcadd websocket server: fix for model loading (just overriding args didn't do it after all...)
ben_mkiv created pull request ecker/ai-voice-cloning#341 2023-08-24 08:05:31 +00:00
fix filename generation which didn't work and overwrote existing files
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-24 07:58:23 +00:00
00b173857d fix filename generation which didn't work and overwrote existing files
ben_mkiv commented on pull request ecker/ai-voice-cloning#336 2023-08-23 17:42:42 +00:00
favor existing arguments from parameters (kwargs) over global (args)

thank you, i've reduced the PR to overriding the args parameters in the websocket server, ignore the commit spam... squashed it down to one commit

ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:41:21 +00:00
ce24ba41e2 Websocket server, override args parameters for model settings (squashed)
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:29:40 +00:00
d16ba3a06d Websocket server, override args parameters for model settings (squashed)
Compare 2 commits »
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:24:45 +00:00
6a5af79c5c remove unused import
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:23:33 +00:00
a9d2f241a5 Revert "favor existing arguments from parameters (kwargs) over global (args)"
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:21:54 +00:00
a17078a792 Revert "added parameter to specify the autoregressive_model (tho it still loads the default model first, and then loads the target model, which seems to be because TTS loading just loads whatever is set in the settings first)"
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-23 17:11:53 +00:00
f087b45943 Revert "added parameter to specify the autoregressive_model (tho it still loads the default model first, and then loads the target model, which seems to be because TTS loading just loads whatever is set in the settings first)"
ben_mkiv created pull request ecker/ai-voice-cloning#336 2023-08-22 21:41:47 +00:00
favor existing arguments from parameters (kwargs) over global (args)
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-22 21:35:44 +00:00
d1dbe3e464 added parameter to specify the autoregressive_model (tho it still loads the default model first, and then loads the target model, which seems to be because TTS loading just loads whatever is set in the settings first)
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-22 21:12:21 +00:00
89102347a9 favor existing arguments from parameters (kwargs) over global (args)
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-22 19:54:07 +00:00
5d73d9e71c small QoL change to the StringNone helper, to allow generated text to be "None", maybe someone wants to generate that, we never know...
ben_mkiv created pull request ecker/ai-voice-cloning#334 2023-08-22 19:42:01 +00:00
websocket server: API change(!), better response format
ben_mkiv pushed to master at ben_mkiv/ai-voice-cloning 2023-08-22 19:38:41 +00:00
9abcb0f193 websocket server: API change(!), better response format