Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
lpscr created a comment on a pull request on SWivid/F5-TTS
@SWivid understand so user must put manual this option then **epochs** to dont confuse ok maybe i put only **extend** because i think if someone train the model from the scratch so with have a ...
huutuongtu created a comment on an issue on SWivid/F5-TTS
> So you are training from scratch or finetuning on pretrained model. A possible reason is: the low loss is for overfitting if you use small batchsize. I trained a model from scratch using two A...
jpgallegoar created a comment on a pull request on SWivid/F5-TTS
@SWivid Now load time is faster and less memory usage, also doesn't download the LLM model unless you use it first time
jpgallegoar pushed 3 commits to main SWivid/F5-TTS
jpgallegoar closed a pull request on SWivid/F5-TTS
Added a Load button for the chat tab
This will speed up loading times and optimize memory usage for users who don't want to use that feature
jpgallegoar closed a pull request on SWivid/F5-TTS
Added a Load button for the chat tab
This will speed up loading times and optimize memory usage for users who don't want to use that feature
SWivid created a comment on a pull request on SWivid/F5-TTS
@jpgallegoar is it ready for merge? dont mind for the formatter, i'll just take care of it
SWivid created a comment on a pull request on SWivid/F5-TTS
@lpscr `wanted_max_updates = 1000000` is just up to user's need (say, what ever you want, hard to tell which is better, cuz every use different dataset with different size) the script we put th...
trunks970 created a comment on an issue on SWivid/F5-TTS
> @trunks970 some similar issues, try online space demo in huggingface/modelscope. > > Probably with whisper asr failure or network stuffs... so a few things got it to work on my pc (3070) bu...
trunks970 closed an issue on SWivid/F5-TTS
No Synthesized Audio
Not sure if I should post this here or elsewhere but im very new to programs like this and whenever i upload a reference audio then attempt to synthesize it I get nothing, I should mention I am usi...
SWivid created a comment on an issue on SWivid/F5-TTS
So you are training from scratch or finetuning on pretrained model. A probably reason is: the low loss is for overfitting if you use small batchsize.
SWivid created a comment on an issue on SWivid/F5-TTS
@kmn1024 Ah yes, that makes sense. Maybe the best way is to filter out null audio samples or we just remove the contraint <0.3?
SWivid created a comment on an issue on SWivid/F5-TTS
@trunks970 some similar issues, try online space demo in huggingface/modelscope. Probably with whisper asr failure or network stuffs...
lpscr created a comment on a pull request on SWivid/F5-TTS
@SWivid also about the vocab new from dataset i think be good to extend with vocab for Emilia_ZH_EN_pinyin for example if there is new symbols not in let to add this from train from the scrat...
jpgallegoar created a comment on a pull request on SWivid/F5-TTS
@SWivid This speeds inference a lot, good idea
jpgallegoar pushed 3 commits to main SWivid/F5-TTS
jpgallegoar closed a pull request on SWivid/F5-TTS
Added audio caching for faster inference
Added audio caching in utils_infer so if the same audio is used twice, it will not be transcribed again.
lpscr opened a pull request on SWivid/F5-TTS
new update gradiof finetune
just another great update fix some stuf first add create vocan from the dataset and you can see  s...
jpgallegoar closed a pull request on SWivid/F5-TTS
Added audio cashing for faster inference
Added audio caching in utils_infer so if the same audio is used twice, it will not be transcribed again.
jpgallegoar opened a pull request on SWivid/F5-TTS
Added audio cashing for faster inference
Added audio caching in utils_infer so if the same audio is used twice, it will not be transcribed again.