Commit @fa128ddd0fe2e20e6d4c5b645918882c573c0879 - yjyoon/whisper_streaming

Dominik Macháček 2023-06-02

Update README.md

update server description

@fa128ddd0fe2e20e6d4c5b645918882c573c0879

e68952a

fa128dd

README.md

--- README.md

+++ README.md


 
 The backend is loaded only when chosen. The unused one does not have to be installed.
 
-## Usage: example entry point
+## Usage
+
+### Realtime 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}]

 
 [See description here](https://github.com/ufal/whisper_streaming/blob/d915d790a62d7be4e7392dde1480e7981eb142ae/whisper_online.py#L361)
 
-## Usage as a module
+### As a module
 
 TL;DR: use OnlineASRProcessor object and its methods insert_audio_chunk and process_iter. 
 

 online.init()  # refresh if you're going to re-use the object for the next audio
 ```
 
-## Usage: Server
+### Server
 
-`whisper_online_server.py` entry point has the same model option sas the entry point above, plus `--host` and `--port`, and no audio path.
+`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection.
 
 Client example:
 

 arecord -f S16_LE -c1 -r 16000 -t raw -D default | nc localhost 43001
 ```
 
-- 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
+- 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)
 
-- nc is netcat, server host and port are e.g. localhost 430001
+- nc is netcat with server's host and port
 
 
 ## Background

Add a comment

Open 0
Closed 0

List

...	...	@@ -16,7 +16,9 @@
16	16
17	17	The backend is loaded only when chosen. The unused one does not have to be installed.
18	18
19		-## Usage: example entry point
	19	+## Usage
	20	+
	21	+### Realtime simulation from audio file
20	22
21	23	```
22	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}]
...	...	@@ -72,7 +74,7 @@
72	74
73	75	[See description here](https://github.com/ufal/whisper_streaming/blob/d915d790a62d7be4e7392dde1480e7981eb142ae/whisper_online.py#L361)
74	76
75		-## Usage as a module
	77	+### As a module
76	78
77	79	TL;DR: use OnlineASRProcessor object and its methods insert_audio_chunk and process_iter.
78	80
...	...	@@ -110,9 +112,9 @@
110	112	online.init() # refresh if you're going to re-use the object for the next audio
111	113	```
112	114
113		-## Usage: Server
	115	+### Server
114	116
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.
	117	+`whisper_online_server.py` has the same model options as `whisper_online.py`, plus `--host` and `--port` of the TCP connection.
116	118
117	119	Client example:
118	120
...	...	@@ -120,9 +122,9 @@
120	122	arecord -f S16_LE -c1 -r 16000 -t raw -D default \| nc localhost 43001
121	123	```
122	124
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
	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)
124	126
125		-- nc is netcat, server host and port are e.g. localhost 430001
	127	+- nc is netcat with server's host and port
126	128
127	129
128	130	## Background

Delete comment