typos
Browse files
README.md
CHANGED
@@ -252,12 +252,12 @@ To deploy WhisperLiveKit in production:
|
|
252 |
|
253 |
### ๐ Docker
|
254 |
|
255 |
-
A basic Dockerfile is provided which allows re-use of
|
256 |
|
257 |
-
|
258 |
|
259 |
#### All defaults
|
260 |
-
- Create a
|
261 |
```bash
|
262 |
docker build -t whisperlivekit-defaults .
|
263 |
docker create --gpus all --name whisperlivekit -p 8000:8000 whisperlivekit-defaults
|
@@ -267,17 +267,17 @@ docker start -i whisperlivekit
|
|
267 |
> **Note**: If you're running on a system without NVIDIA GPU support (such as Mac with Apple Silicon or any system without CUDA capabilities), you need to **remove the `--gpus all` flag** from the `docker create` command. Without GPU acceleration, transcription will use CPU only, which may be significantly slower. Consider using small models for better performance on CPU-only systems.
|
268 |
|
269 |
#### Customization
|
270 |
-
-
|
271 |
```bash
|
272 |
docker build -t whisperlivekit-defaults .
|
273 |
docker create --gpus all --name whisperlivekit-base -p 8000:8000 whisperlivekit-defaults --model base
|
274 |
docker start -i whisperlivekit-base
|
275 |
```
|
276 |
|
277 |
-
- `--build-arg` Options
|
278 |
- `EXTRAS="whisper-timestamped"` - Add extras to the image's installation (no spaces). Remember to set necessary container options!
|
279 |
-
- `HF_PRECACHE_DIR
|
280 |
-
- `HF_TOKEN
|
281 |
|
282 |
## ๐ฎ Use Cases
|
283 |
|
|
|
252 |
|
253 |
### ๐ Docker
|
254 |
|
255 |
+
A basic Dockerfile is provided which allows re-use of Python package installation options. See below usage examples:
|
256 |
|
257 |
+
**NOTE:** For **larger** models, ensure that your **docker runtime** has enough **memory** available.
|
258 |
|
259 |
#### All defaults
|
260 |
+
- Create a reusable image with only the basics and then run as a named container:
|
261 |
```bash
|
262 |
docker build -t whisperlivekit-defaults .
|
263 |
docker create --gpus all --name whisperlivekit -p 8000:8000 whisperlivekit-defaults
|
|
|
267 |
> **Note**: If you're running on a system without NVIDIA GPU support (such as Mac with Apple Silicon or any system without CUDA capabilities), you need to **remove the `--gpus all` flag** from the `docker create` command. Without GPU acceleration, transcription will use CPU only, which may be significantly slower. Consider using small models for better performance on CPU-only systems.
|
268 |
|
269 |
#### Customization
|
270 |
+
- Customize the container options:
|
271 |
```bash
|
272 |
docker build -t whisperlivekit-defaults .
|
273 |
docker create --gpus all --name whisperlivekit-base -p 8000:8000 whisperlivekit-defaults --model base
|
274 |
docker start -i whisperlivekit-base
|
275 |
```
|
276 |
|
277 |
+
- `--build-arg` Options:
|
278 |
- `EXTRAS="whisper-timestamped"` - Add extras to the image's installation (no spaces). Remember to set necessary container options!
|
279 |
+
- `HF_PRECACHE_DIR="./.cache/"` - Pre-load a model cache for faster first-time start
|
280 |
+
- `HF_TOKEN="./token"` - Add your Hugging Face Hub access token to download gated models
|
281 |
|
282 |
## ๐ฎ Use Cases
|
283 |
|