anime-whisper-ggml

ใ“ใฎใƒขใƒ‡ใƒซใฏใ€litagin/anime-whisperใ‚’whisper.cppใ‚’ไฝฟใฃใฆggmlๅค‰ๆ›ใƒป้‡ๅญๅŒ–ใ‚’่กŒใฃใŸใƒขใƒ‡ใƒซใงใ™ใ€‚

ๆŽจ่ซ–ใฎๅ‹•ไฝœ่‡ชไฝ“ใฏ็ขบ่ชใ—ใฆใ„ใพใ™ใŒใ€ๆ–‡ๅญ—่ตทใ“ใ—็ตๆžœใŒใ‚„ใ‚„ใŠใ‹ใ—ใใชใ‚‹ๅ•้กŒใ‚’ๆŠฑใˆใฆใ„ใพใ™๏ผˆๅ…ˆ้ ญใซ่ฌŽใฎๆ–‡ๅญ—ใŒๅ…ฅใ‚‹ใชใฉ๏ผ‰ใ€‚่งฃๆฑบ็ญ–็ญ‰ๅˆ†ใ‹ใ‚‹ๆ–นใ„ใ‚Œใฐๆ•™ใˆใฆใใ ใ•ใ„ใ€‚

ๅค‰ๆ›ๆ‰‹้ †

ๅคงๆœฌใฎใƒขใƒ‡ใƒซใงใ‚ใ‚‹kotoba-tech/kotoba-whisper-v2.0-ggmlใฎREADMEใ‚’ๅ‚่€ƒใซใ€ไปฅไธ‹ใฎใ‚ˆใ†ใชๆ‰‹้ †ใงๅค‰ๆ›ใƒป้‡ๅญๅŒ–ใ—ใฆใ„ใพใ™ใ€‚

# clone OpenAI whisper and whisper.cpp
git clone https://github.com/openai/whisper
git clone https://github.com/ggerganov/whisper.cpp

# get the models
cd whisper.cpp/models
huggingface-cli download litagin/anime-whisper --local-dir ./anime-whisper

# convert to ggml
python ./convert-h5-to-ggml.py ./anime-whisper/ ../../whisper .
mv ggml-model.bin ggml-anime-whisper.bin

# quantize ggml model
cd ../
cmake -B build -DGGML_CUDA=1
cmake --build build -j --config Release
./build/bin/quantize models/ggml-anime-whisper.bin models/ggml-anime-whisper-q8_0.bin q8_0
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 Aratako/anime-whisper-ggml

Finetuned
(2)
this model