Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
rlenain opened an issue on SWivid/F5-TTS
Tracking validation loss?
Hello, and thanks a lot for open sourcing this work. I am using the `finetune-cli.py` script, which works great! I'm only able to track the training loss, and don't see validation loss being cal...
SWivid closed a pull request on SWivid/F5-TTS
very quick fix in gradio_finetune.py
i just fix empty value when i delete need be **tts_api = None**
lpscr opened a pull request on SWivid/F5-TTS
very quick fix in gradio_finetune.py
i just fix empty value when i delete need be **tts_api = None**
SWivid created a comment on a pull request on SWivid/F5-TTS
@lpscr yes ~ you could just pr, offer a tensorboard option while take wandb as default, in order to keep it neat and also functional
SWivid created a comment on a pull request on SWivid/F5-TTS
@lpscr we actually use tensorboard earlier, as you can see there is `/runs` in `.gitignore` lol though we have wandb now but I actually not see it anymore for reasons in #9 (no significant signals...
lpscr created a comment on a pull request on SWivid/F5-TTS
@SWivid yes thank you working ! one think i know it's not the place to talk about but something quick i make also train working with tensorboard , so you can change easy wandb or tensorboard , ...
SWivid created a comment on a pull request on SWivid/F5-TTS
@lpscr the entrance is mainly `infer_process()` so I just add `device=self.device` and remove device checking in utils_infer.py see 608e224f9d3c46d6357334a049ffa260aa284d94
PierrunoYT created a comment on an issue on SWivid/F5-TTS
> > Im using it with Pinokio > > > > Not sure if pinokio also compatible with training/finetuning. > > > > If you just want to do inference, use `gradio_app.py` and `inference-cli.py` Yes it...
lpscr created a comment on a pull request on SWivid/F5-TTS
@SWivid work thank you sorry for the misake i just do a lot stuff same time and i miss this part . but same eror **cpu and cuda:0!** when you change device