Phoneme input error
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 37.8k
- Forks
- 4.3k
- Avg merge
- 7m
- Merged PRs (30d)
- 1
Description
Hi,
Thanks for your great work.
I ran into an issue with the Native mode when inputting Chinese Pinyin with tone numbers, for instance: "这几日 {zuo1} 坊里多了个小客人 —— 隔壁搬来的小女孩念念。小姑娘扎着羊角辫，总踮着脚扒着 {zuo4} 坊门槛", the synthesized audio pronounces the tone numbers (1 and 4) as literal digits instead of applying the corresponding tones to the syllable "zuo".
I’m wondering if yout team has tested this scenario before, and if there’s a way to avoid this problem?
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
Reproduce the reported Native-mode input using the provided Pinyin examples, including {zuo1} and {zuo4}, and compare the generated audio with the attached sample. Trace how phoneme input is handled before synthesis, then verify that tone numbers are interpreted as tones rather than spoken as digits and that the regression is covered by a test or reproducible check.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100