Dominik Macháček commited on
Commit
a365074
·
1 Parent(s): 819ac6c

Update README.md

Browse files

update server description

Files changed (1) hide show
  1. README.md +8 -6
README.md CHANGED
@@ -16,7 +16,9 @@ Alternative, less restrictive, but slowe backend is [whisper-timestamped](https:
16
 
17
  The backend is loaded only when chosen. The unused one does not have to be installed.
18
 
19
- ## Usage: example entry point
 
 
20
 
21
  ```
22
  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}]
@@ -72,7 +74,7 @@ python3 whisper_online.py en-demo16.wav --language en --min-chunk-size 1 > out.t
72
 
73
  [See description here](https://github.com/ufal/whisper_streaming/blob/d915d790a62d7be4e7392dde1480e7981eb142ae/whisper_online.py#L361)
74
 
75
- ## Usage as a module
76
 
77
  TL;DR: use OnlineASRProcessor object and its methods insert_audio_chunk and process_iter.
78
 
@@ -110,9 +112,9 @@ print(o) # do something with the last output
110
  online.init() # refresh if you're going to re-use the object for the next audio
111
  ```
112
 
113
- ## Usage: Server
114
 
115
- `whisper_online_server.py` entry point has the same model option sas the entry point above, plus `--host` and `--port`, and no audio path.
116
 
117
  Client example:
118
 
@@ -120,9 +122,9 @@ Client example:
120
  arecord -f S16_LE -c1 -r 16000 -t raw -D default | nc localhost 43001
121
  ```
122
 
123
- - arecord is an example program that sends audio from a sound device, in raw audio format -- 16000 sampling rate, mono channel, S16\_LE -- signed 16-bit integer low endian
124
 
125
- - nc is netcat, server host and port are e.g. localhost 430001
126
 
127
 
128
  ## Background
 
16
 
17
  The backend is loaded only when chosen. The unused one does not have to be installed.
18
 
19
+ ## Usage
20
+
21
+ ### Realtime simulation from audio file
22
 
23
  ```
24
  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}]
 
74
 
75
  [See description here](https://github.com/ufal/whisper_streaming/blob/d915d790a62d7be4e7392dde1480e7981eb142ae/whisper_online.py#L361)
76
 
77
+ ### As a module
78
 
79
  TL;DR: use OnlineASRProcessor object and its methods insert_audio_chunk and process_iter.
80
 
 
112
  online.init() # refresh if you're going to re-use the object for the next audio
113
  ```
114
 
115
+ ### Server
116
 
117
+ `whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection.
118
 
119
  Client example:
120
 
 
122
  arecord -f S16_LE -c1 -r 16000 -t raw -D default | nc localhost 43001
123
  ```
124
 
125
+ - arecord sends realtime audio from a sound device, in raw audio format -- 16000 sampling rate, mono channel, S16\_LE -- signed 16-bit integer low endian. (use the alternative to arecord that works for you)
126
 
127
+ - nc is netcat with server's host and port
128
 
129
 
130
  ## Background