README.md

metadata

title: Kikuyu Speech To Text
emoji: 🎤
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 5.49.1
python_version: 3.11
app_file: app.py
pinned: false
models:
  - Kiragu/whisper-small-kikuyu-v5
datasets:
  - thiomi/thiomi-5k

Kikuyu Speech To Text

A Gradio Space for testing Kikuyu automatic speech recognition with Kiragu/whisper-small-kikuyu-v5.

Upload or record audio, optionally paste the correct Thiomi transcript, and compare the model output against the reference text.