Belle-whisper-large-v3-turbo-zh-ggml-quantized
The quantized (q5_0, q5_1, q8_0) GGML version of Belle-whisper-large-v3-turbo-zh, used for whisper.cpp
More info about the model, please refer to https://huggingface.co/BELLE-2/Belle-whisper-large-v3-turbo-zh
Model tree for uosx/Belle-whisper-large-v3-turbo-zh-ggml-quantized
Base model
openai/whisper-large-v3
Finetuned
openai/whisper-large-v3-turbo
Finetuned
BELLE-2/Belle-whisper-large-v3-turbo-zh