LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-03-07 14:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into TIAGo-WE-COBOT

Browse Source
This commit is contained in:
Dominik Macháček
2023-11-28 11:03:58 +01:00
parent 18c1434f77 878f11cdb7
commit bd0d848e7f
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -42,7 +42,7 @@ The unused one does not have to be installed. We integrate the following segment
## Usage
### Realtime simulation from audio file
### Real-time simulation from audio file
```
usage: whisper_online.py [-h] [--min-chunk-size MIN_CHUNK_SIZE] [--model {tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large}] [--model_cache_dir MODEL_CACHE_DIR] [--model_dir MODEL_DIR] [--lan LAN] [--task {transcribe,translate}]
@@ -126,14 +126,14 @@ from whisper_online import *
src_lan = "en" # source language
tgt_lan = "en" # target language -- same as source for ASR, "en" if translate task is used
asr = FasterWhisperASR(lan, "large-v2") # loads and wraps Whisper model
# set options:
# asr.set_translate_task() # it will translate from lan into English
# asr.use_vad() # set using VAD
# asr.use_vad() # set using VAD
tokenizer = create_tokenizer(tgt_lan) # sentence segmenter for the target language
online = OnlineASRProcessor(tgt_lan, asr) # create processing object
online = OnlineASRProcessor(asr, tokenizer) # create processing object
while audio_has_not_ended: # processing loop:
@@ -149,7 +149,7 @@ print(o) # do something with the last output
online.init() # refresh if you're going to re-use the object for the next audio
```
### Server
### Server -- real-time from mic
`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection. See help message (`-h` option).