Deployed on edge devices
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.3k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
Checks
- This template is only for question, not feature requests or bug reports.
- I have thoroughly reviewed the project documentation and read the related paper(s).
- I have searched for existing issues, including closed ones, no similar questions.
- I confirm that I am using English to submit this report in order to facilitate communication.
Question details
Hello, everyone. I want to ask, has anyone successfully deployed the F5-TTS model on edge devices? Such as deploy on qualcomm chips using QNN？I have used QNN to deployed F5_Transformer part on SM8550 with HTP fp16 precision, but the latency is too heavy to accept, it takes me about 5s to run F5_Transformer once(my test audio length is about 6s).
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the F5_Transformer deployment on Qualcomm SM8550 with QNN and HTP fp16 described in the issue. Compare the reported 5-second latency for 6-second audio with the project's documented deployment guidance; done would require an agreed edge-device deployment approach and acceptable latency target.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, embedded-iot
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100