#
moedict
Here are 9 public repositories matching this topic...
Chinese family (Mandarin/Taiwanese/Hakka) podcast transcription with speaker diarization. Built-in 172k+15k vocab from 教育部辭典 + FrequencyWords. Whisper large-v3-turbo + pyannote 3.3.
cog podcast vocabulary chinese speech-to-text transcription whisper mandarin moedict replicate hakka diarization pyannote
-
Updated
May 25, 2026 - Python
Add this topic to your repo
To associate your repository with the moedict topic, visit your repo's landing page and select "manage topics."