microsoft / microsoft/markitdown
[Feature Request] Customized Audio Transcription Provider
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 186k
- Forks
- 13.7k
- Avg merge
- 1d 4h
- Merged PRs (30d)
- 49
Description
Current implementation:
https://github.com/microsoft/markitdown/blob/62b72284feb986ffaf8c22fa73614545b5713c30/packages/markitdown/src/markitdown/converters/_transcribe_audio.py#L48
The problem is that, when my audio is not in English, it still try to transcribe to English. Is it possible to implement some configurable options to change to other provider? The SpeechRecognition library provides a couple of alternative. Technically, it should not be hard to implement... The problem is how to make the configuration intuitive and easy to understand...
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 packages/markitdown/src/markitdown/converters/_transcribe_audio.py at the linked implementation. Review how transcription is currently configured and how alternative providers could be exposed; done means users can select a provider or language through an intuitive configuration and non-English audio is handled accordingly.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100