ChivoxAI
sign in

/docs

cn.pred.raw

Kernel Description

Evaluate the Chinese paragraph/chapter, outputting scores of overall, fluency, accuracy, integrity, each sentence and ench Chinese character;

  • Support difficulty adjustment;
  • Support missed reading detection;
  • Support real-time feedback of Chinese characters that have been read and evaluation scores；

Request Parameters

Parameter Type Required Description
coreType String true cn.pred.raw means Chinese paragraph kernel.
refText String true Supports scoring of Chinese paragraphs within 1000 words, punctuation marks need to be passed in, supported punctuation marksClick to view
rank int false Point system，support 100
attachAudioUrl number false Enable to return audio url or not.
  • 0: Disable
  • 1: Enable
result object false Return result detailed settings
- details object false Detailed scoring options
- - word int false Whether to output the score of each Chinese character, Default is 0
  • 0: Disable.
  • 1: Enabled
- - gop_adjust number false Increase or reduce the evaluation scores.
value range[-1,-0.9, ... 0.9, 1]。
Default value is 0, which means using original scores.
The passing parameter is a positive number to increase the scoring score. The larger the passing parameter, the more the score will be improved.
Pass parameter is negative, reduce the scoring score, the smaller the pass parameter, the more the score will be reduced
- - ext_cur_wrd number false Enable to return the words that have been read in real time，Default value is 0. Support multiple modes
0: Disable.
1: General mode, the returned results are output from front to back in the order of the text;
2: Recitation mode, the returned results are strictly in accordance with the text order from front to back; if the previous sentence is missed, even if the following sentence is read normally, it will not be returned;
3: Free mode, returns the content of reference text actually read by users, regardless of the order of text;

Sample Code

Sample1 Chinese text
{
  "coreType": "cn.pred.raw", 
  "refText": "今天天气很好，特别好。", 
  "rank": 100, 
  "attachAudioUrl": 1, 
  "result": {
    "details": {	
      "word": 1,
	  "ext_cur_wrd":1,
	  "gop_adjust":0
    }
  }
}
Sample2 Customize the pinyin of a Chinese character
{
  "coreType": "cn.pred.raw", 
  "refText": "今天天气很好，特别好。风吹草低见(xian4)牛羊，思援弓缴(zhuo2)而射之。", 
  "rank": 100, 
  "attachAudioUrl": 1, 
  "result": {
    "details": {
      "word": 1,
	  "ext_cur_wrd":0,
	  "gop_adjust":0
    }
  }
}
Sample3 Customize the pinyin of non-Chinese character text
{
  "coreType": "cn.pred.raw", 
  "refText": {
    "text": "今天天气很好，特别好。呼叫10087，hello一心以为有鸿鹄将至。", 
    "prons": [
      {
        "10087": "yao1 ling2 ling2 ba1 qi1"
      }, 
      {
        "hello": "ha1 lou2"
      }
    ]
  }, 
  "rank": 100, 
  "attachAudioUrl": 1, 
  "result": {
    "details": {
      "word": 1,
	  "ext_cur_wrd":0,
	  "gop_adjust":0
    }
  }
}
Sample4 Custom pinyin for single characters and non-single Chinese characters
{
  "coreType": "cn.pred.raw", 
  "refText": {
    "text": "今天天气很好，特别好。呼叫10087，hello一心以为有鸿鹄将至。真牛X(cha1)。", 
    "prons": [
      {
        "10087": "yao1 ling2 ling2 ba1 qi1"
      }, 
      {
        "hello": "ha1 lou2"
      }
    ]
  }, 
  "rank": 100, 
  "attachAudioUrl": 1, 
  "result": {
    "details": {
      "word": 1,
	  "ext_cur_wrd":0,
	  "gop_adjust":0
    }
  }
}

Introduction to Real-time return Results

Key Type Description Recommendations
eof int Whether the final evaluation result
0: Indicates that the result is returned in real time during the recording process;
1: Indicates that the result is the final evaluation result after the recording is completed;		 Suggest to display
result object Scoring result
- rec string During the evaluation process, the newly-recognized Chinese characters will be returned in real time Suggest to display
- phnspeed string Current speaking rate For reference
- details object Real-time return the content that has been read
- - chn_char string Chinese character Suggest to display
- - char string Pinyin Suggest to display
- - tone number Standard tone value (0~4) Suggest to display
- - score number Chinese character score Suggest to display
- - beginindex number Take refText as a character array, beginindex represents the index of the first character of the word
in refText, and the index starts from 0. For convenience
The application layer echoes refText as it is		 Suggest to display
- - endindex number Regarding the refText field as a character array, endindex represents the index of the end of Chinese character
in refText, starting from 0. For convenience
The application layer echoes refText as it is

Example of Real-time return Results

{
	"sdk": {
		"protocol": "websocket",
		"version": 16777216,
		"source": 4
	},
	"tokenId": "29****a1-****-****-****-****7e****fc",
	"result": {
		"details": [[{
			"chn_char": "快",
			"tone": 4,
			"endindex": 2,
			"char": "kuai",
			"score": 100,
			"group": 0,
			"beginindex": 0
		},
		......
		{
			"chn_char": "年",
			"tone": 2,
			"endindex": 8,
			"char": "nian",
			"score": 100,
			"group": 0,
			"beginindex": 6
		}]],
		"rec": "快过年",
		"phnspeed": 338
	},
	"eof": 0,
	"time": {
		"callback": "2021-04-13 15:03:31:325",
		"start": "2021-04-13 15:03:28:283",
		"connect": "2021-04-13 15:03:28:203"
	}
}

Example of Returned Results

  • The results are returned using the JSON structure,Example

Introduction to Returned Results

Key Type Description Recommendations
uuid string Unique id of audio. Save uuid in database in case of need. For reference
audioUrl string Audio url.

Download audio in http protocol: Just add ".mp3" at the end of the URL.
Download audio in https protocol: Remove the port number, add ".mp3" at the end, and add "https://" to the prefix.
e.g.https://download.cloud.chivox.com/XXXXXXXX.mp3

Tips:
  • Chivox save audio for one week. Please save audio to your own server for long-term storage.
  • The domain name will be different for different access areas, and the actual return shall prevail.
 For reference
- wavetime number Audio duration (Unit:milliseconds) For reference
- overall number Overall score Suggest to display
- fluency object Score of fluency.
- - pause number Number of pauses. Suggest to display
- - overall number Overall score of fluency Suggest to display
- - speed number Speech rate, which is the number of words read per minute. Suggest to display
- integrity number Score of integrity. Suggest to display
- accuracy number Score of accuracy(pronunciation evaluation of the read parts). Suggest to display
- tone number Tone score Suggest to display
- phn number Pronunciation score without tone Suggest to display
- details array object
- - chn_text string Chinese sentence
- - py_text string Chinese Sentence Pinyin For reference
- - phn number Pronunciation score without tone For reference
- - overall number sentence score For reference
- - tone number Tone score For reference
- - start number Start time of the sentence in the audio (Unit: milliseconds) For reference
- - end number End time of the sentence in the audio (Unit: milliseconds) For reference
- - dur number duration (Unit: milliseconds). For reference
- - is_leak number Mark if this sentence is missed
  • 0:Not missed reading
  • 1:Missed reading
 For reference
- - beginindex number Take refText as a character array, beginindex represents the index of the first character of the word
in refText, and the index starts from 0. For convenience
The application layer echoes refText as it is		 For reference
- - endindex number Regarding the refText field as a character array, endindex represents the index of the end of Chinese character
in refText, starting from 0. For convenience
The application layer echoes refText as it is		 For reference
- - words array Result of each Chinese character
- - - chn_char string Chinese character For reference
- - - char string Pinyin For reference
- - - overall number Chinese character score For reference
- - - is_err number Error Type
0: Correct
1: superfluous reading
2: missing reading		 For reference
- - - tonescore number Tone score For reference
- - - phn number Pronunciation score without tone For reference
- - - confidence array Pronunciation tone confidence, a total of 5 digits,
respectively indicate the probability of being pronounced as soft, one, two, three, and four tones.
The tone with the largest number is the actual tone of the pronunciation.		 Suggest to display
- - - tone number Standard tone value (0~4) For reference
- - - start number The start time of the word in audio (Unit:milliseconds). For reference
- - - end number The end time of the word in audio (Unit: milliseconds). For reference
- - - dur number duration (Unit: milliseconds). For reference
- - - beginindex number Take refText as a character array, beginindex represents the index of the first character of the word
in refText, and the index starts from 0. For convenience
The application layer echoes refText as it is		 For reference
- - - endindex number Regarding the refText field as a character array, endindex represents the index of the end of Chinese character
in refText, starting from 0. For convenience
The application layer echoes refText as it is		 For reference
- info object
- - tipId number Audio quality
For details, please refer toTipId field description		 For reference
- - tips string Error message prompt
When prompted "post proc failed", it may be that the audio was not successfully recorded or the engine did not detect the user’s valid voice.
Prompt the user to re-record		 For reference

Note: The other returned parameters that are not shown above are internal ones, which you don't need to pay much atttention to.

SDK, API, MCP and Function Calling documentation on this site.