Whisper GGML Quants - a Pomni Collection

Pomni 's Collections

Whisper Finetune GGML Quants

Whisper GGML Quants

distil-whisper GGML Quants

Whisper GGML Quants

updated Aug 29

GGML quants of the official Whisper models, ranging from Q2_K all the way to F32.

Pomni/whisper-large-v3-turbo-ggml-allquants

Automatic Speech Recognition • Updated Aug 29 • 1

Note Turbo's accuracy should be similar to regular Large v3 while being double the speed, unless you're transcribing non-English speech, noisy audio, or music.
Pomni/whisper-large-v3-ggml-allquants

Automatic Speech Recognition • Updated Aug 27
Pomni/whisper-large-v2-ggml-allquants

Automatic Speech Recognition • Updated Aug 29
Pomni/whisper-large-ggml-allquants

Automatic Speech Recognition • Updated Aug 29
Pomni/whisper-medium-ggml-allquants

Automatic Speech Recognition • Updated Aug 25
Pomni/whisper-medium.en-ggml-allquants

Automatic Speech Recognition • Updated Aug 24
Pomni/whisper-small-ggml-allquants

Automatic Speech Recognition • Updated Aug 21
Pomni/whisper-small.en-ggml-allquants

Automatic Speech Recognition • Updated Aug 16
Pomni/whisper-base-ggml-allquants

Automatic Speech Recognition • Updated Aug 16
Pomni/whisper-base.en-ggml-allquants

Automatic Speech Recognition • Updated Aug 15
Pomni/whisper-tiny-ggml-allquants

Automatic Speech Recognition • Updated Aug 15
Pomni/whisper-tiny.en-ggml-allquants

Automatic Speech Recognition • Updated Aug 15