Merge remote-tracking branch 'upstream/main' into add_default_server
This commit is contained in:
|
Before Width: | Height: | Size: 3.0 KiB After Width: | Height: | Size: 3.0 KiB |
@@ -38,7 +38,6 @@ Unlike traditional speech recognition systems that rely on continuous audio stre
|
|||||||
python client.py --host "localhost" --port "9090"
|
python client.py --host "localhost" --port "9090"
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
## Transcribe audio from browser
|
## Transcribe audio from browser
|
||||||
- Run the server
|
- Run the server
|
||||||
```bash
|
```bash
|
||||||
@@ -47,11 +46,10 @@ Unlike traditional speech recognition systems that rely on continuous audio stre
|
|||||||
This would start the websocket server on port ```9090```.
|
This would start the websocket server on port ```9090```.
|
||||||
|
|
||||||
### Chrome Extension
|
### Chrome Extension
|
||||||
- Head over to ```Audio-Transcription``` module to unpack and load a chrome extension to capture any audio in the browser and send it to the websocket server to transcribe the audio in the current tab.
|
- Refer to [Audio-Transcription-Chrome](https://github.com/collabora/whisper-live/tree/main/Audio-Transcription-Chrome#readme) to use Chrome extension.
|
||||||
|
|
||||||
### Firefox Extension
|
### Firefox Extension
|
||||||
- Refer to [Audio-Transcription-Firefox](https://github.com/collabora/whisper-live/tree/main/Audio-Transcription-Firefox#readme) to use mozilla firefox extension.
|
- Refer to [Audio-Transcription-Firefox](https://github.com/collabora/whisper-live/tree/main/Audio-Transcription-Firefox#readme) to use Mozilla Firefox extension.
|
||||||
|
|
||||||
|
|
||||||
## Whisper Live Server in Docker
|
## Whisper Live Server in Docker
|
||||||
- Build docker container
|
- Build docker container
|
||||||
@@ -64,7 +62,6 @@ This would start the websocket server on port ```9090```.
|
|||||||
docker run -it --gpus all -p 9090:9090 whisper-live:latest
|
docker run -it --gpus all -p 9090:9090 whisper-live:latest
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|
||||||
## Future Work
|
## Future Work
|
||||||
- [ ] Update Documentation.
|
- [ ] Update Documentation.
|
||||||
- [x] Keep only a single server implementation i.e. websockets and get rid of the socket implementation in ```server.py```. Also, update ```client.py``` to websockets-client implemenation.
|
- [x] Keep only a single server implementation i.e. websockets and get rid of the socket implementation in ```server.py```. Also, update ```client.py``` to websockets-client implemenation.
|
||||||
@@ -76,7 +73,7 @@ This would start the websocket server on port ```9090```.
|
|||||||
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
|
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
|
||||||
url = {https://arxiv.org/abs/2212.04356},
|
url = {https://arxiv.org/abs/2212.04356},
|
||||||
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
|
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
|
||||||
publisher = {arXiv},
|
publisher = {arXiv},
|
||||||
year = {2022},
|
year = {2022},
|
||||||
}
|
}
|
||||||
```
|
```
|
||||||
@@ -91,4 +88,4 @@ This would start the websocket server on port ```9090```.
|
|||||||
howpublished = {\url{https://github.com/snakers4/silero-vad}},
|
howpublished = {\url{https://github.com/snakers4/silero-vad}},
|
||||||
commit = {insert_some_commit_here},
|
commit = {insert_some_commit_here},
|
||||||
email = {hello@silero.ai}
|
email = {hello@silero.ai}
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user