# ASR text correct/edit recipe

**URL:** <https://support.prodi.gy/t/asr-text-correct-edit-recipe/5833>\
**Category:** Uncategorized\
**Tags:** usage, audio\
**Created:** [July 28, 2022, 9:23pm UTC](https://support.prodi.gy/t/asr-text-correct-edit-recipe/5833 "2022-07-28T21:23:08Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![ryanwesslen](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ryanwesslen/32/2969_2.png) [@ryanwesslen](https://support.prodi.gy/u/ryanwesslen)\
**Post date:** [July 29, 2022, 7:25pm UTC](https://support.prodi.gy/t/asr-text-correct-edit-recipe/5833/6 "2022-07-29T19:25:42Z")

</div>

The most efficient approach may be to create a Python script as a [custom loader](https://prodi.gy/docs/api-loaders#loaders-custom) using [`pydub`](https://stackoverflow.com/questions/2952309/python-library-to-split-and-join-mp3-files) to slice the segments by looping through each `start_second` and `end_second` pair. Make sure you return [an iterable stream](https://prodi.gy/docs/api-loaders#loaders-file) for your loader.

Alternatively, you could use `pydub` to create a directory with separate `.mp3` files for each segment. Then you could use the `audio.transcribe` to load the directory without needing a loader.

---

_[View the full topic](https://support.prodi.gy/t/asr-text-correct-edit-recipe/5833)._