OpenMOSS / OpenMOSS/MOSS-Transcribe-Diarize
What should be the prompt to transcribe in another language than Chinese or English?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 126
- Avg merge
- 17h 42m
- Merged PRs (30d)
- 5
Description
The file with example prompts only give examples in Chinese and English. I played a bit with those prompts and have difficulty on enforcing the model to transcribe in French (when the language in the audio is French).
Is there a way to specify the (source and target) language in the prompt? For example in French, what should I use for speaker-only transcription and timestamped diarization?
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 with examples/prompts.md and review the existing Chinese and English prompt examples. Add French examples for speaker-only transcription and timestamped diarization, clarifying how source and target languages should be specified; done means the requested multilingual prompt guidance is documented there.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 76/100