Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
LSliu666 created a comment on an issue on SWivid/F5-TTS
Yeah, I can change the homophone to his homophone.thanks
LSliu666 created a comment on an issue on SWivid/F5-TTS
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...
SWivid created a comment on an issue on SWivid/F5-TTS
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
SWivid created a comment on an issue on SWivid/F5-TTS
What do you mean with `code inference`, the `infer-cli`?
SWivid created a comment on an issue on SWivid/F5-TTS
Currently no such feature in Gradio yet. Welcome PR~
SWivid created a comment on an issue on SWivid/F5-TTS
@PhamDangNguyen Sure, or you could just use the code, and train from scratch
LSliu666 created a comment on an issue on SWivid/F5-TTS
I am using Gradio. How to indicate the pinyin of the text so that I won't read it incorrectly
mhenrichsen created a comment on an issue on SWivid/F5-TTS
I can confirm that after removing all audio lower than 0.3 and higher than 30 it runs fine. Thanks for the help.
mhenrichsen closed an issue on SWivid/F5-TTS
VRAM usage randomly spikes. Continues fine after restart.
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 ...
PhamDangNguyen created a comment on an issue on SWivid/F5-TTS
> 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...
SWivid created a comment on an issue on SWivid/F5-TTS
will close this issue, if further questions feel free to open
SWivid closed an issue on SWivid/F5-TTS
Will not work without reference text.
Any time I try to generate audio without a reference text (using gradio) I get the following message: You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 5...
SWivid created a comment on an issue on SWivid/F5-TTS
will close as solved, feel free to open if further questions
SWivid created a comment on an issue on SWivid/F5-TTS
will close as solved, feel free to open if further questions
SWivid closed an issue on SWivid/F5-TTS
Ability to specify finetuned model in the Gradio app
Hello, I've come to this repo recently, so apologies if I've missed something here. Things sound great, although I'm currently doing some finetuning tests from the original f5tts checkpoint with ...
ehsanahmadkhan525 created a comment on an issue on SWivid/F5-TTS
Looking for the same solution can we implement streaming on F5? Please guide
