---

whisper-large-zh-cv11-GGML

Original Model

jonatasgrosman/whisper-large-zh-cv11

Run with LlamaEdge

• LlamaEdge-Whisper version: coming soon

• Run as LlamaEdge service

  wasmedge --dir .:. whisper-api-server.wasm --model ggml-whisper-large-zh-cv11-Q8_0.bin
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
ggml-whisper-large-zh-cv11-Q2_K.bin	Q2_K	2	529 MB
ggml-whisper-large-zh-cv11-Q3_K.bin	Q3_K	3	685 MB	Recommended
ggml-whisper-large-zh-cv11-Q4_0.bin	Q4_0	4	889 MB
ggml-whisper-large-zh-cv11-Q4_1.bin	Q4_1	4	985 MB
ggml-whisper-large-zh-cv11-Q4_K.bin	Q4_K	4	889 MB	Recommended
ggml-whisper-large-zh-cv11-Q5_0.bin	Q5_0	5	1.08 GB
ggml-whisper-large-zh-cv11-Q5_1.bin	Q5_1	5	1.18 GB
ggml-whisper-large-zh-cv11-Q5_K.bin	Q5_K	5	1.08 GB	Recommended
ggml-whisper-large-zh-cv11-Q6_K.bin	Q6_K	6	1.28 GB	Recommended
ggml-whisper-large-zh-cv11-Q8_0.bin	Q8_0	8	1.66 GB	Recommended
ggml-whisper-large-zh-cv11.bin	f16	16	3.09 GB	Recommended

Quantized with whisper.cpp 0377596b