facebookresearch / facebookresearch/fairseq2
load an Audio with fairseq2.data.AudioDecoder with specific offset and duration
Open
enhancement
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 144
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 1
Description
I have numerous audio files along with their corresponding subtitles. I need to load specific segments of these audio files, defined by particular offsets and durations. However, the current python AudioDecoder interface doesn't support this functionality. Loading entire audio files is not feasible due to their large sizes.
Contributor guide
Assessment
This issue has not been assessed yet.