whisper.cpp/models
Georgi Gerganov 93482d0373
models : add "convert-h5-to-ggml.py" script (#157)
Converts transformers models to ggml.
Although the conversion is successful, it does not work for some reason.
Not sure why
2022-11-23 17:19:22 +02:00
..
.gitignore Initial release 2022-09-25 22:13:49 +03:00
convert-h5-to-ggml.py models : add "convert-h5-to-ggml.py" script (#157) 2022-11-23 17:19:22 +02:00
convert-pt-to-ggml.py models : simplify the conversion script 2022-11-16 19:22:32 +02:00
download-ggml-model.cmd models : change default hosting to Hugging Face 2022-11-15 19:47:06 +02:00
download-ggml-model.sh Update download-ggml-model.sh 2022-11-16 18:59:44 +02:00
for-tests-ggml-base.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-base.en.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-large.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-medium.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-medium.en.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-small.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-small.en.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-tiny.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
for-tests-ggml-tiny.en.bin Adding dummy models for testing purposes 2022-10-08 11:43:42 +03:00
README.md models : change default hosting to Hugging Face 2022-11-15 19:47:06 +02:00

Whisper model files in custom ggml format

The original Whisper PyTorch models provided by OpenAI have been converted to custom ggml format in order to be able to load them in C/C++. The conversion has been performed using the convert-pt-to-ggml.py script. You can either obtain the original models and generate the ggml files yourself using the conversion script, or you can use the download-ggml-model.sh script to download the already converted models. Currently, they are hosted on the following locations:

Sample usage:

$ ./download-ggml-model.sh base.en
Downloading ggml model base.en ...
models/ggml-base.en.bin          100%[=============================================>] 141.11M  5.41MB/s    in 22s
Done! Model 'base.en' saved in 'models/ggml-base.en.bin'
You can now use it like this:

  $ ./main -m models/ggml-base.en.bin -f samples/jfk.wav

A third option to obtain the model files is to download them from Hugging Face:

https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main

Available models

Model Disk Mem SHA
tiny 75 MB ~390 MB bd577a113a864445d4c299885e0cb97d4ba92b5f
tiny.en 75 MB ~390 MB c78c86eb1a8faa21b369bcd33207cc90d64ae9df
base 142 MB ~500 MB 465707469ff3a37a2b9b8d8f89f2f99de7299dac
base.en 142 MB ~500 MB 137c40403d78fd54d454da0f9bd998f78703390c
small 466 MB ~1.0 GB 55356645c2b361a969dfd0ef2c5a50d530afd8d5
small.en 466 MB ~1.0 GB db8a495a91d927739e50b3fc1cc4c6b8f6c2d022
medium 1.5 GB ~2.6 GB fd9727b6e1217c2f614f9b698455c4ffd82463b4
medium.en 1.5 GB ~2.6 GB 8c30f0e44ce9560643ebd10bbe50cd20eafd3723
large 2.9 GB ~4.7 GB b1caaf735c4cc1429223d5a74f0f4d0b9b59a299

Model files for testing purposes

The model files pefixed with for-tests- are empty (i.e. do not contain any weights) and are used by the CI for testing purposes. They are directly included in this repository for convenience and the Github Actions CI uses them to run various sanitizer tests.