Note Our caption engine in the browser: Whisper via Transformers.js, word-by-word captions, .ass/.srt export.

onnx-community/whisper-base

Automatic Speech Recognition • Updated 5 days ago • 223k • 33

Note The in-browser Whisper behind the captions Space (tiny and small are options too).

Systran/faster-whisper-small

Automatic Speech Recognition • Updated Nov 23, 2023 • 5.66M • 87

Note Desktop transcripts and word timings for Clipper, captions and Smart Video, via faster-whisper.

openbmb/VoxCPM-0.5B

Text-to-Speech • Updated Aug 18 • 5.3k • 829

Note Voice cloning from a 10-30 s reference clip, run fully on-device.

bluryar/VoxCPM-GGUF

Text-to-Speech • 0.7B • Updated Apr 21 • 3.17k • 18

Note The quantized VoxCPM weights the desktop app runs through a ggml port.