Update default model download paths to `~/.cache/whisper`

CHANGELOG.md

@@ -7,6 +7,12 @@ Unreleased
 ### Updated
 
 - Updated model conversion method (for Faster Whisper) to use Hugging Face downloader
+- Updated default model paths to `~/.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
+    ```
 
 ### Changed
 

README.md

@@ -179,10 +179,18 @@ docker run -d --gpus all -p 9000:9000 -e ASR_MODEL=base whisper-asr-webservice-g
 ```
 
 ## 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 (/root/.cache/whisper) to an persistent storage. Next time you start your container the ASR Model will be taken from the cache instead of being downloaded again.
+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. 
+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.**
  
 ```sh
-docker run -d -p 9000:9000 -e ASR_MODEL=large -v //c/tmp/whisper:/root/.cache/whisper onerahmet/openai-whisper-asr-webservice:latest
+docker run -d -p 9000:9000 -v ./yourlocaldir:~/.cache/whisper onerahmet/openai-whisper-asr-webservice:latest
+```
+
+or
+
+```sh
+docker run -d -p 9000:9000 -e ASR_MODEL_PATH=/data/whisper -v ./yourlocaldir:/data/whisper onerahmet/openai-whisper-asr-webservice:latest
 ```

app/faster_whisper/core.py

@@ -10,7 +10,7 @@ from faster_whisper import WhisperModel
 from .utils import ResultWriter, WriteTXT, WriteSRT, WriteVTT, WriteTSV, WriteJSON
 
 model_name = os.getenv("ASR_MODEL", "base")
-model_path = os.getenv("ASR_MODEL_PATH", "/root/.cache/whisper")
+model_path = os.getenv("ASR_MODEL_PATH", os.path.join(os.path.expanduser("~"), ".cache", "whisper"))
 
 if torch.cuda.is_available():
     model = WhisperModel(model_size_or_path=model_name, device="cuda", compute_type="float32", download_root=model_path)

app/openai_whisper/core.py

@@ -8,10 +8,12 @@ import whisper
 from whisper.utils import ResultWriter, WriteTXT, WriteSRT, WriteVTT, WriteTSV, WriteJSON
 
 model_name = os.getenv("ASR_MODEL", "base")
+model_path = os.getenv("ASR_MODEL_PATH", os.path.join(os.path.expanduser("~"), ".cache", "whisper"))
+
 if torch.cuda.is_available():
-    model = whisper.load_model(model_name).cuda()
+    model = whisper.load_model(model_name, download_root=model_path).cuda()
 else:
-    model = whisper.load_model(model_name)
+    model = whisper.load_model(model_name, download_root=model_path)
 model_lock = Lock()
 
 

docker-compose.gpu.yml

@@ -15,13 +15,12 @@ services:
     environment:
       - ASR_MODEL=base
     ports:
-      - 9000:9000
+      - "9000:9000"
     volumes:
       - ./app:/app/app
       - cache-pip:/root/.cache/pip
       - cache-poetry:/root/.cache/poetry
-      - cache-whisper:/root/.cache/whisper
-      - cache-faster-whisper:/root/.cache/faster_whisper
+      - cache-whisper:~/.cache/whisper
 
 volumes:
   cache-pip:

docker-compose.yml

@@ -8,13 +8,12 @@ services:
     environment:
       - ASR_MODEL=base
     ports:
-      - 9000:9000
+      - "9000:9000"
     volumes:
       - ./app:/app/app
       - cache-pip:/root/.cache/pip
       - cache-poetry:/root/.cache/poetry
-      - cache-whisper:/root/.cache/whisper
-      - cache-faster-whisper:/root/.cache/faster_whisper
+      - cache-whisper:~/.cache/whisper
 
 volumes:
   cache-pip: