ivrit.ai whisper-large-v3-turbo, 8-bit (q8_0) GGML

ivrit-large-v3-turbo-q8_0.bin is a q8_0 copy of ivrit-ai/whisper-large-v3-turbo-ggml (ggml-model.bin), made with whisper.cpp v1.9.5 whisper-quantize. For whisper.cpp on a processor: about half the time and 60% of the memory of the full-size file, with the same text on our test clips.

sha256: 123a936e686b06d45b52dc1790251a1418841352ca94079ae643d57893ffc9a6

All credit for the model goes to ivrit.ai. License: Apache-2.0, as the original.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for davidpu/wa-voice-ggml

Finetuned
(4)
this model