Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
ehsanahmadkhan525 created a comment on a pull request on SWivid/F5-TTS
Also need to add CORS as well.
ehsanahmadkhan525 opened a pull request on SWivid/F5-TTS
FastAPI for inferencing and add new voices
its working just need to refactor a bit
HaileyStorm closed an issue on SWivid/F5-TTS
ARPAbet phoneme pronunciation not working.
When I try to generate text with ARPAbet phones in parenthesis like you see in the "Specifying the pronunciation without model re-training" of https://www.microsoft.com/en-us/research/project/e2-tt...
SWivid commented on a commit on SWivid/F5-TTS
Hi @fakerybakery ~ We have got some updates, and the original `gradio_app.py` is now here `src/f5_tts/infer/infer_gradio.py` Wondering if you could help tweak the synchronization to the Hugging...
SWivid pushed 15 commits to main SWivid/F5-TTS
- convert to pkg, reorganize repo (#228) * group files in f5_tts directory * add setup.py * use global imports ... c4eee0f
- . d8638a6
- Delete tests directory 213adf4
- make a structure first 8ed1bea
- final structure. prepared to solve dependencies 8e0edfc
- tweak d3951b9
- tweak c1ba121
- Add back /data for local editable use case ff690b7
- update infer_gradio b4abb3c
- update finetune-cli -gradio 254e5e6
- finish eval dependencies; update infer_gradio with chat feature ba4b04b
- finish train dependencies a846ae6
- tweak api.py e78110e
- minor fix for finetune_gradio.py da500b5
- initial updates for infer stuffs 8629c6f
SWivid created a branch on SWivid/F5-TTS
previous_main - Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
RootingInLoad created a comment on an issue on SWivid/F5-TTS
Hello everyone, you can do everything you desire with the Podcast Generation feature. When I created it, it was because F5-TTS just came out, and that I wanted to try that feature out. You ca...
SWivid created a comment on an issue on SWivid/F5-TTS
@chigkim @jpgallegoar @RootingInLoad I will just switch to a new repo structure, which is more fine-grained, and with pip pkg support
jpgallegoar created a comment on an issue on SWivid/F5-TTS
I agree we could improve the experience by consolidating those and improving instructions. Perhaps even make the creation of said scripts easier by making the {Speaker} tags appear with the click o...
SWivid created a comment on an issue on SWivid/F5-TTS
> Maybe I should reprocess the dataset and filter out audio with a duration less than 0.3 Two possible reasons: - dataset contains null samples. - torchaudio just go crazy again, fail to load ...
chigkim created a comment on an issue on SWivid/F5-TTS
@RootingInLoad, Would it be okay to consolidate the Podcast tab into the Multi-Style tab and remove the Podcast tab? Currently, the Multi-Style tab is described as being for emotions, but it actua...
