Skip to main content

Oreille is a wrapper on OpenAPI Whisper API. It's provide support for long audio files.

Project description

OpenAPI Whisper support only files that are less than 25 MB. Oreille will break the audio file into chunks of 25 MB’s or less.

https://platform.openai.com/docs/guides/speech-to-text/longer-inputs Oreille will also compute the correct timing of the subtitle when merging the output of Whisper. So once you export the subtitle the timestamp of the subtitle will be right. You can open and save WAV files with pure python. For opening and saving non-wav files – like mp3 – you’ll need ffmpeg or libav.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

oreille-0.2.0.tar.gz (5.7 kB view details)

Uploaded Source

File details

Details for the file oreille-0.2.0.tar.gz.

File metadata

  • Download URL: oreille-0.2.0.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for oreille-0.2.0.tar.gz
Algorithm Hash digest
SHA256 f91b2a32e07ec5d608c4c45e36705cf222eebe9f0b7b2c772793dd9339f78574
MD5 75a05cdcf5cc8a5e863d3b0996ecd8d2
BLAKE2b-256 f0b2aa1d7ccf26f7187664facec6f5fa5ea4319b35211cf8a1263908b19e25f0

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page