README.md

metadata

title: Transcription | Speech to Text | OpenAI Whisper
emoji: 🗣️
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 5.30.0
app_file: app.py
python_version: 3.9.9
pinned: false
license: unlicense
short_description: Minimum working OpenAI Whisper pipeline

Minimum OpenAI Whisper

I've found most Hugging Face Spaces to be unsatisfactory, mainly due to rampant overcomplexity.

So I've written this space to be the minimum working OpenAI Whisper pipeline. Internally it does not pass redundant parameters or include extra features, and it does attempt to provide a simple (Gradio.)interface, in a space that actually works if you duplicate it.