Skip to content

Issues: SWivid/F5-TTS

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

23 Open 590 Closed
23 Open 590 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Audio Output Silent After Upgrading to 1.0+ – Potential Architecture/Configuration Changes? question Further information is requested
#896 opened Mar 21, 2025 by atlonxp
4 tasks done
2
GPU inference on infer help wanted Extra attention is needed
#894 opened Mar 20, 2025 by Skylighter18
4 tasks done
4
General Feedback enhancement New feature or request
#893 opened Mar 20, 2025 by Dencel-CleverAI
4 of 5 tasks
finetune_gradio samples enhancement New feature or request
#892 opened Mar 20, 2025 by sarpba
4 of 5 tasks
Does it allow detecting word or sentence boundaries during TTS generation? help wanted Extra attention is needed
#887 opened Mar 20, 2025 by securealex
4 tasks done
3
How to Ensure Consistent Speech Speed in F5-TTSv1? question Further information is requested
#876 opened Mar 18, 2025 by atfeel
4 tasks done
1
The advantage in V1 version question Further information is requested
#868 opened Mar 17, 2025 by yiwei0730
4 tasks done
15
Fine-tune with another language help wanted Extra attention is needed
#849 opened Mar 14, 2025 by vuminhnghiawork
4 tasks done
12
add new language and finetune based on pretrained model question Further information is requested
#817 opened Feb 26, 2025 by yiershanxll
4 tasks done
10
Sugession About Segmenting TTS Output into Sentences for Easier Editing enhancement New feature or request
#813 opened Feb 25, 2025 by DonChoudhry
5 tasks done
6
FlashMLA enhancement New feature or request
#812 opened Feb 24, 2025 by atlonxp
5 tasks done
2
Gradio automatically finds pretrained models to use enhancement New feature or request
#730 opened Jan 17, 2025 by holycowdude
4 of 5 tasks
6
Is the ~15 Second Clipping of Logged Audio Samples During Training Intentional? question Further information is requested
#719 opened Jan 14, 2025 by hcsolakoglu
4 tasks done
2
Deployed on edge devices documentation Improvements or additions to documentation question Further information is requested
#694 opened Jan 6, 2025 by Francis235
4 tasks done
2
Convert vocos checkpoint to bigvgan; bigvgan with vocos-style mel spectrograms documentation Improvements or additions to documentation enhancement New feature or request
#654 opened Dec 20, 2024 by kmn1024
4 tasks done
4
LoRA support question Further information is requested
#621 opened Dec 12, 2024 by MithrilMan
4 tasks done
3
We are trying to use sentiment text to make the generated audio have different emotions enhancement New feature or request
#606 opened Dec 8, 2024 by xwan07017
5 tasks done
14
Will there be an entension model like E2 TTS X2 question Further information is requested
#576 opened Dec 3, 2024 by Jinming00
4 tasks done
Training from scratch for English model, somewhat listenable after 180k updates. help wanted Extra attention is needed
#548 opened Nov 28, 2024 by Quentin1168
4 tasks done
22
EQ correction on the reference audio is crucial for achieving high-quality results. enhancement New feature or request
#378 opened Nov 2, 2024 by anderssoft
7
how to f5 tts train for other language
#291 opened Oct 27, 2024 by Chiyan200
48
Export to ONNX Format enhancement New feature or request
#214 opened Oct 22, 2024 by DakeQQ
44
Supported Languages?
#87 opened Oct 15, 2024 by AlonDan
101
ProTip! no:milestone will show everything without a milestone.