AI가 움직이고 미래가 업데이트됩니다.whisper-large-v3-turbo-int8-ov
This is whisper-large-v3-turbo model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3 with the number of decoder layers reduced from 32 to 4, which makes the model significantly faster at the expense of a minor quality degradation. The original model is distributed under MIT license. More details can be found in original model card.
번역 준비 중입니다. 원문을 표시합니다.
This is whisper-large-v3-turbo model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3 with the number of decoder layers reduced from 32 to 4, which makes the model significantly faster at the expense of a minor quality degradation. The original model is distributed under MIT license. More details can be found in original model card.