EveryVoiceTTS / EveryVoiceTTS/EveryVoice
We should be able to provide our own character or phone tokens
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 45
- Forks
- 4
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 14
Description
Description & Motivation
I have a dataset that already has tokenized phones, and while using a filelist with phone_tokens works, it's not documented anywhere, and some things are a little cumbersome (to_replace only works on phones/characters for example, not pre-computed phone_tokens)
Pitch
No response
Alternatives
No response
Additional context
No response
Contributor guide
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 tracing how filelist entries with phone_tokens are parsed and where to_replace is applied. Confirm the expected behavior for user-supplied character or phone tokens, then document the supported filelist path and ensure replacements work with precomputed phone_tokens.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100