Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2024-01-25 4f078d1cbd4dfd1ffce31a563cc792098174f920

 runtime/docs/websocket_protocol.md

@@ -36,7 +36,7 @@
#### Sending Recognition Results
The message (serialized in JSON) is:
```text
{"mode": "offline", "wav_name": "wav_name", "text": "asr ouputs", "is_final": True, "timestamp":"[[100,200], [200,500]]"}
{"mode": "offline", "wav_name": "wav_name", "text": "asr ouputs", "is_final": True, "timestamp":"[[100,200], [200,500]]", "stamp_sents":[]}
```
Parameter explanation:
```text
@@ -45,6 +45,7 @@
`text`: the text output of speech recognition
`is_final`: indicating the end of recognition
`timestamp`：If AM is a timestamp model, it will return this field, indicating the timestamp, in the format of "[[100,200], [200,500]]"
`stamp_sents`：If AM is a timestamp model, it will return this field, indicating the stamp_sents, in the format of [{"text_seg":"正 是 因 为","punc":",","start":430,"end":1130,"ts_list":[[430,670],[670,810],[810,1030],[1030,1130]]}]
```

## Real-time Speech Recognition
@@ -84,7 +85,7 @@
The message (serialized in JSON) is:

```text
{"mode": "2pass-online", "wav_name": "wav_name", "text": "asr ouputs", "is_final": True, "timestamp":"[[100,200], [200,500]]"}
{"mode": "2pass-online", "wav_name": "wav_name", "text": "asr ouputs", "is_final": True, "timestamp":"[[100,200], [200,500]]", "stamp_sents":[]}
```
Parameter explanation:
```text
@@ -93,4 +94,5 @@
`text`: the text output of speech recognition
`is_final`: indicating the end of recognition
`timestamp`：If AM is a timestamp model, it will return this field, indicating the timestamp, in the format of "[[100,200], [200,500]]"
`stamp_sents`：If AM is a timestamp model, it will return this field, indicating the stamp_sents, in the format of [{"text_seg":"正 是 因 为","punc":",","start":430,"end":1130,"ts_list":[[430,670],[670,810],[810,1030],[1030,1130]]}]
```