mirrors/whispering
1
0
Fork 0
mirror of https://github.com/shirayu/whispering.git synced 2024-06-12 10:19:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated

Browse source
This commit is contained in:
Yuta Hayashibe 2022-09-25 00:55:37 +09:00
parent 8483238e84
commit 48d31edfeb
1 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
README.md
View file

@ -24,7 +24,7 @@ poetry run pip install -U torch torchaudio --extra-index-url https://download.py
```bash ```bash
# Run in English # Run in English
poetry run whisper_streaming --language en --model base poetry run whisper_streaming --language en --model tiny
``` ```
- ``--help`` shows full options - ``--help`` shows full options
@ -38,25 +38,25 @@ If you want quick response, set small ``-n`` and add ``--allow-padding``.
However, this may be at the sacrifice of accuracy. However, this may be at the sacrifice of accuracy.
```bash ```bash
poetry run whisper_streaming --language en --model base -n 20 --allow-padding poetry run whisper_streaming --language en --model tiny -n 20 --allow-padding
``` ```
## Example of web socket ## Example of web socket
⚠ **No security mechanism. Please make secure with your responsibility.** ⚠ **No security mechanism. Please make secure with your responsibility.**
### Host
Run with ``--host`` and ```--port``. You can set``-n`` and other options as use with microphone. Run with ``--host`` and ```--port``. You can set``-n`` and other options as use with microphone.
### Host
```bash ```bash
poetry run whisper_streaming --language en --model base --host 0.0.0.0 --port 8000 poetry run whisper_streaming --language en --model tiny --host 0.0.0.0 --port 8000 --allow-padding
``` ```
### Client ### Client
```bash ```bash
poetry run python -m whisper_streaming.websocket_client --host ADDRESS_OF_HOST --port 8000 poetry run python -m whisper_streaming.websocket_client --host ADDRESS_OF_HOST --port 8000 -n 20
``` ```
## Tips ## Tips