Skip to content
Snippets Groups Projects
Commit 78c7205f authored by Ahmet Oner's avatar Ahmet Oner
Browse files

Update cache folder usage, Fixes #138

parent 8ed32c63
No related branches found
No related tags found
No related merge requests found
......@@ -20,11 +20,11 @@ Unreleased
### Updated
- Updated model conversion method (for Faster Whisper) to use Hugging Face downloader
- Updated default model paths to `~/.cache/whisper`.
- Updated default model paths to `~/.cache/whisper` or `/root/.cache/whisper`.
- For customization, modify the `ASR_MODEL_PATH` environment variable.
- Ensure Docker volume is set for the corresponding directory to use caching.
```bash
docker run -d -p 9000:9000 -e ASR_MODEL_PATH=/data/whisper -v ./yourlocaldir:/data/whisper onerahmet/openai-whisper-asr-webservice:latest
docker run -d -p 9000:9000 -e ASR_MODEL_PATH=/data/whisper -v $PWD/yourlocaldir:/data/whisper onerahmet/openai-whisper-asr-webservice:latest
```
- Removed the `triton` dependency from `poetry.lock` to ensure the stability of the pipeline for `ARM-based` Docker images
......
......@@ -20,7 +20,7 @@ services:
- ./app:/app/app
- cache-pip:/root/.cache/pip
- cache-poetry:/root/.cache/poetry
- cache-whisper:~/.cache/whisper
- cache-whisper:/root/.cache/whisper
volumes:
cache-pip:
......
......@@ -13,7 +13,7 @@ services:
- ./app:/app/app
- cache-pip:/root/.cache/pip
- cache-poetry:/root/.cache/poetry
- cache-whisper:~/.cache/whisper
- cache-whisper:/root/.cache/whisper
volumes:
cache-pip:
......
......@@ -35,7 +35,7 @@ Docker Hub: <https://hub.docker.com/r/onerahmet/openai-whisper-asr-webservice>
## Cache
The ASR model is downloaded each time you start the container, using the large model this can take some time.
If you want to decrease the time it takes to start your container by skipping the download, you can store the cache directory (`~/.cache/whisper`) to a persistent storage.
If you want to decrease the time it takes to start your container by skipping the download, you can store the cache directory (`~/.cache/whisper` or `/root/.cache/whisper`) to a persistent storage.
Next time you start your container the ASR Model will be taken from the cache instead of being downloaded again.
**Important this will prevent you from receiving any updates to the models.**
......@@ -43,7 +43,7 @@ Next time you start your container the ASR Model will be taken from the cache in
=== ":octicons-file-code-16: `Default cache dir`"
```sh
docker run -d -p 9000:9000 -v ./yourlocaldir:~/.cache/whisper onerahmet/openai-whisper-asr-webservice:latest
docker run -d -p 9000:9000 -v $PWD/yourlocaldir:/root/.cache/whisper onerahmet/openai-whisper-asr-webservice:latest
```
=== ":octicons-file-code-16: `With ASR_MODEL_PATH`"
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment