extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-01-14 01:48:32 +01:00
Code Issues Packages Projects Releases Wiki Activity

models : add instructions for using HF fine-tuned models

Browse Source
This commit is contained in:
Georgi Gerganov 2022-11-24 17:54:41 +02:00
parent 128aaadb93
commit a2ecd54455
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 21 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
models/README.md
View File

@ -41,5 +41,24 @@ https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main
## Model files for testing purposes ## 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. The model files prefixed with `for-tests-` are empty (i.e. do not contain any weights) and are used by the CI for
They are directly included in this repository for convenience and the Github Actions CI uses them to run various sanitizer tests. testing purposes. They are directly included in this repository for convenience and the Github Actions CI uses them to
run various sanitizer tests.
## Fine-tuned models
There are community efforts for creating fine-tuned Whisper models using extra training data. For example, this
[blog post](https://huggingface.co/blog/fine-tune-whisper) describes a method for fine-tuning using Hugging Face (HF)
Transformer implementation of Whisper. The produced models are in slightly different format compared to the original
OpenAI format. To read the HF models you can use the [convert-h5-to-ggml.py](convert-h5-to-ggml.py) script like this:
```
git clone https://github.com/openai/whisper
git clone https://github.com/ggerganov/whisper.cpp
# clone HF fine-tuned model (this is just an example)
git clone https://huggingface.co/openai/whisper-base.en
# convert the model to ggml
python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium/ ./whisper .
```