whisper.cpp / models

Commit History

docs : make model options / model install methods clearer (#1806)
a2bec1d
unverified

mikey-rrr commited on

models : make all scripts to be POSIX Compliant (#1725)
f7aef3e
unverified

sonphantrung commited on

coreml : fix ANE optimized encoder (#1716)
a75904e
unverified

philloooo commited on

download : fix large q5 model name (#1695)
5df6c6c
unverified

DimoP commited on

docker : Dockerize whisper.cpp (#1674)
7163150
unverified

Chaoqun commited on

models : add info about distilled models
8c251e2
unverified

ggerganov commited on

whisper : make large version explicit + fix data size units (#1493)
03a3210
unverified

ggerganov commited on

openvino : update convert-whisper-to-openvino.py to support v3 (#1459)
b9f3d1b
unverified

bobqianic commited on

coreml : use the correct `n_mel` value (#1458)
0220892
unverified

mljxy commited on

whisper : add support for large v3 (#1444)
9908abb
unverified

ggerganov commited on

models : use absolute paths for the converted model (#1356)
6023f2d
unverified

bobqianic commited on

models : Faster download for models on windows using BitTransfer (#1404)
b1a3c5a
unverified

WhiteOlivierus commited on

models : add conversion scripts from HuggingFace models to CoreML (#1304)
756cd4b
unverified

AlienKevin commited on

models : add quantum models to download-ggml-model.sh (#1235)
b2abb1b
unverified

Neil Chudleigh commited on

whisper : add OpenVINO support (#1037)
49bcee6
unverified

Ryan Metcalfe ggerganov commited on

whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058)
eedbf0c
unverified

Akash Mahajan ggerganov commited on

models : add ggml_to_pt script (#1042)
95e087e
unverified

Simon Moisselin simonn94 commited on

models : cd statements are quoted to allow spaces in path (#1041)
3063d29
unverified

Roddur Dasgupta commited on

models : handle paths with spaces in download script (close #1038)
097a82d
unverified

ggerganov commited on

py : make convert-pt-to-ggml.py backwards compatible with older vocab.json tokenizer files (#1001)
83e4988
unverified

akashmjn commited on

models : fix README.md (#964)
9cc4aaa
unverified

genevera (she/her) commited on

coreml : add support of large-v1 model (#926)
7935008
unverified

Ahmad Bilal commited on

readme : add instructions on converting to GGML + "--no-config" to wget (#874)
d94de9a
unverified

Clifford Heath commited on

minor : improve C++ and Python style (#768)
3ebe4d6
unverified

AsukaMinato commited on

whisper : add Core ML support (#566)
1fd4bde
unverified

ggerganov commited on

models : change convert-pt-to-ggml to use .tiktoken tokenizer files (#725)
a7879d3
unverified

Ivan Gorin commited on

models : handle spaces and special characters in shell script paths (#677)
b829a0a
unverified

be-next commited on

models : change default encoding to utf8 (#605)
2800fe4
unverified

Kamilake commited on

models : change HF hosting from dataset to model
92e3777
unverified

ggerganov commited on

models : fix HF model URL (close #356)
691ac92
unverified

ggerganov commited on

models : fix typo in convert-h5-to-ggml.py
dc8eb84

eltociear commited on

models : fix support for spaces in path (close #315)
f39e0be
unverified

ggerganov commited on

talk : improve prompting
de68a7e
unverified

ggerganov commited on

Fix paths echoed after the download
e508930

Kartik Saranathan commited on

models : add the new "large" model release by OpenAI
793fa90
unverified

ggerganov commited on

talk.wasm : move to https://whisper.ggerganov.com/talk
bee1ba7
unverified

ggerganov commited on

models : add instructions for using HF fine-tuned models
bd9b418
unverified

ggerganov commited on

models : add usage comments to the HF convert script (#157)
8528ec5
unverified

ggerganov commited on

models : fix HF fine-tuned model conversion script (#157)
6c811ac
unverified

ggerganov commited on

models : minor changes to the HF convert script (#157)
f500082
unverified

ggerganov commited on

models : add "convert-h5-to-ggml.py" script (#157)
3568438
unverified

ggerganov commited on

models : simplify the conversion script
1ffa4c8
unverified

ggerganov commited on

Update download-ggml-model.sh
23d667f

Dody Suria Wijaya commited on

models : change default hosting to Hugging Face
7cf1c53
unverified

ggerganov commited on

minor : remove one more redundant line
6f3392b
unverified

ggerganov commited on

minor : fix double float32 conversion in python script
e6c2e3e
unverified

ggerganov commited on

extra : compute SHA of all models files
05261df
unverified

ggerganov commited on

Added for Windows implemenated script download-ggml-model.cmd
cdf540e

Mikhail Grigorev commited on

Changes to work by default on macOS - use curl when wget is not available, and use an alternative method to get the script path when realpath is not available.
7b2581f

andypayne commited on

refactoring : move main + stream in examples + other stuff
f79068a

ggerganov commited on