Cleanup commands in README
Browse files
README.md
CHANGED
|
@@ -44,7 +44,8 @@ python cli.py --model large --vad silero-vad --language Japanese "https://www.yo
|
|
| 44 |
You can also run both the Web-UI or the CLI on multiple GPUs in parallel, using the `vad_parallel_devices` option. This takes a comma-delimited list of
|
| 45 |
device IDs (0, 1, etc.) that Whisper should be distributed to and run on concurrently:
|
| 46 |
```
|
| 47 |
-
python cli.py --model large --vad silero-vad --language Japanese
|
|
|
|
| 48 |
```
|
| 49 |
|
| 50 |
Note that this requires a VAD to function properly, otherwise only the first GPU will be used. Though you could use `period-vad` to avoid taking the hit
|
|
@@ -90,8 +91,11 @@ sudo docker run -d --gpus=all -p 7860:7860 registry.gitlab.com/aadnk/whisper-web
|
|
| 90 |
|
| 91 |
You can also pass custom arguments to `app.py` in the Docker container, for instance to be able to use all the GPUs in parallel:
|
| 92 |
```
|
| 93 |
-
sudo docker run -d --gpus all -p 7860:7860
|
| 94 |
-
|
|
|
|
|
|
|
|
|
|
| 95 |
```
|
| 96 |
|
| 97 |
You can also call `cli.py` the same way:
|
|
@@ -110,5 +114,7 @@ Note that the models themselves are currently not included in the Docker images,
|
|
| 110 |
To avoid this, bind the directory /root/.cache/whisper to some directory on the host (for instance /home/administrator/.cache/whisper), where you can (optionally)
|
| 111 |
prepopulate the directory with the different Whisper models.
|
| 112 |
```
|
| 113 |
-
sudo docker run -d --gpus=all -p 7860:7860
|
|
|
|
|
|
|
| 114 |
```
|
|
|
|
| 44 |
You can also run both the Web-UI or the CLI on multiple GPUs in parallel, using the `vad_parallel_devices` option. This takes a comma-delimited list of
|
| 45 |
device IDs (0, 1, etc.) that Whisper should be distributed to and run on concurrently:
|
| 46 |
```
|
| 47 |
+
python cli.py --model large --vad silero-vad --language Japanese \
|
| 48 |
+
--vad_parallel_devices 0,1 "https://www.youtube.com/watch?v=4cICErqqRSM"
|
| 49 |
```
|
| 50 |
|
| 51 |
Note that this requires a VAD to function properly, otherwise only the first GPU will be used. Though you could use `period-vad` to avoid taking the hit
|
|
|
|
| 91 |
|
| 92 |
You can also pass custom arguments to `app.py` in the Docker container, for instance to be able to use all the GPUs in parallel:
|
| 93 |
```
|
| 94 |
+
sudo docker run -d --gpus all -p 7860:7860 \
|
| 95 |
+
--mount type=bind,source=/home/administrator/.cache/whisper,target=/root/.cache/whisper \
|
| 96 |
+
--restart=on-failure:15 registry.gitlab.com/aadnk/whisper-webui:latest \
|
| 97 |
+
app.py --input_audio_max_duration -1 --server_name 0.0.0.0 --vad_parallel_devices 0,1 \
|
| 98 |
+
--default_vad silero-vad --default_model_name large
|
| 99 |
```
|
| 100 |
|
| 101 |
You can also call `cli.py` the same way:
|
|
|
|
| 114 |
To avoid this, bind the directory /root/.cache/whisper to some directory on the host (for instance /home/administrator/.cache/whisper), where you can (optionally)
|
| 115 |
prepopulate the directory with the different Whisper models.
|
| 116 |
```
|
| 117 |
+
sudo docker run -d --gpus=all -p 7860:7860 \
|
| 118 |
+
--mount type=bind,source=/home/administrator/.cache/whisper,target=/root/.cache/whisper \
|
| 119 |
+
registry.gitlab.com/aadnk/whisper-webui:latest
|
| 120 |
```
|