Ecosyste.ms: Timeline

Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.

SWivid/F5-TTS

SWivid closed an issue on SWivid/F5-TTS
The generated audio always produces an additional pronunciation
From the several test cases I tested, it always emits non-existent characters at the beginning of the audio [zh_prompt.zip](https://github.com/user-attachments/files/17404857/zh_prompt.zip) 给定模型的...
xxXwwwz starred SWivid/F5-TTS
greenbeauty starred SWivid/F5-TTS
eschmidbauer created a comment on an issue on SWivid/F5-TTS
can someone share the onnx export ? i would love to try it out! Thanks

View on GitHub

zobertke starred SWivid/F5-TTS
linan2 starred SWivid/F5-TTS
Lynton6 starred SWivid/F5-TTS
SWivid created a comment on a pull request on SWivid/F5-TTS
@lpscr also check if this works, will turn to that repo structure https://github.com/SWivid/F5-TTS/tree/dev/src/f5_tts/train

View on GitHub

SWivid pushed 2 commits to main SWivid/F5-TTS
  • quick fix device always cpu 7342f8b
  • Merge pull request #252 from lpscr/main quick fix device always cpu ! 732daff

View on GitHub

SWivid closed a pull request on SWivid/F5-TTS
quick fix device always cpu !
@SWivid something i miss here also video action all working great https://github.com/user-attachments/assets/ebf25212-2cc5-4570-b5ff-41b63a6f0f96 BTW: when you have free time please test
SWivid pushed 1 commit to dev SWivid/F5-TTS
  • minor fix for finetune_gradio.py da500b5

View on GitHub

SWivid pushed 1 commit to dev SWivid/F5-TTS

View on GitHub

lpscr created a comment on an issue on SWivid/F5-TTS
@danielw97 check new update in gradio finetune now you can change the model you want https://github.com/SWivid/F5-TTS/discussions/143

View on GitHub

duskcouple starred SWivid/F5-TTS
R7038XX starred SWivid/F5-TTS
lpscr opened a pull request on SWivid/F5-TTS
quick fix device always cpu !
@SWivid something i miss here also video action all working great https://github.com/user-attachments/assets/ebf25212-2cc5-4570-b5ff-41b63a6f0f96
GoodWeather0322 starred SWivid/F5-TTS
keizerzilla starred SWivid/F5-TTS
everestsam starred SWivid/F5-TTS
darkflare starred SWivid/F5-TTS
giibbc starred SWivid/F5-TTS
tuna2134 forked SWivid/F5-TTS

tuna2134/F5-DIFF-TTS-

YellowscorpionDPIII starred SWivid/F5-TTS
SWivid pushed 6 commits to main SWivid/F5-TTS
  • add stystem info , add vocab , suport multi gpu a1eda7d
  • Merge branch 'SWivid:main' into main 7ab0d76
  • Merge branch 'SWivid:main' into main e0b1761
  • update vocab len 0e90c19
  • add setting for mixed precision 43050ed
  • Merge pull request #248 from lpscr/main new update gradio finetune ae59727

View on GitHub

SWivid closed a pull request on SWivid/F5-TTS
new update gradio finetune
@SWivid just another great update and fix some stuf first add create vocan from the dataset and you can see ![image](https://github.com/user-attachments/assets/9784504d-b772-4369-b275-5e8dc...
Fyphen1223 starred SWivid/F5-TTS
lpscr created a comment on a pull request on SWivid/F5-TTS
@SWivid update add mixed_precision option ![image](https://github.com/user-attachments/assets/880ef837-45c1-4c5f-9cb5-c92c9e85e8d6)

View on GitHub

SWivid created a comment on a pull request on SWivid/F5-TTS
> if possible to merge 2 models weight . so not need the dataset English , Chinese ... not sure if will work. a more possible solution is to do llama-adapter finetuning.

View on GitHub

SWivid created a comment on an issue on SWivid/F5-TTS
@huutuongtu I would recommend a smaller model size. And just train longer, at least 200k updates thought to hear something reasonable, cuz we have no phoneme-level force-alignment (if you're int...

View on GitHub

SWivid created a comment on an issue on SWivid/F5-TTS
> oral-to-oral llm chat app Yes, in this way, a streamable tts is better √

View on GitHub

Load more