@LSliu666 Sure, hope this temporary strategy would help.
We don't mean to limit model's ability on that, rather the model is limit with dataset (if you could just provide a bunch of perfect data, ...
Thanks for your efforts @SWivid in transforming the app. However the new version has broken the apps available on huggingface and pinokio. Do you know if its possible to use packaged apps there?
> 追求发音准确而不是单词准确,哈哈,音符
The meaning of this is that I have found an alternative method for mispronouncing polyphonic characters, which is to replace the Chinese character of a polyphonic character...
> @PhamDangNguyen Sure, or you could just use the code, and train from scratch
please show me path to load pre-train model in your repo!! I don't find it :v
> @LSliu666 Mainly for dataset. A good dataset covering most cases and transcribed just correctly will let model do better on this.
@LSliu666 Or you could just provide us with some data, we will...
f5-tts_infer-cli \
--model "F5-TTS" \
--ref_audio "ref_audio.wav" \
--ref_text "The content, subtitle or transcription of reference audio." \
--gen_text "Some text you want TTS model generate f...
Yes, it is just as we suggest above
> Need to see through the code, part as in https://github.com/SWivid/F5-TTS/issues/193.
Or simple you could do like:
好奇 -> 浩奇
Hi,
I'm training on a single A100. I've tried multiple batch sizes, but the same thing keeps happening.
I usually use between 10-25% of all available GPU VRAM, and then all of the sudden it ...
> Hi @PhamDangNguyen . You could just reuse the original vocab.txt if the 88 elements are included in that. If miss some, you could manually replace some vocab you don't want with your own.
this...