@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 ...
> 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...
@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 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...
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 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...
just another great update fix some stuf
first add create vocan from the dataset and you can see
![image](https://github.com/user-attachments/assets/9784504d-b772-4369-b275-5e8dc9dd7d19)
s...