句子多分支评测模式

最近更新时间:2024-11-15 17:59:23

我的收藏

评估模式描述

评测要求:支持多组评估文本,每组不超过30个字。音频数据最长60秒。
评测维度:支持返回单词精准度,流利度,完整度;支持返回音素精准度。
评测功能:多组文本,指定发音。

请求参数

主要请求参数说明:
参数名称
类型
描述
ref_text
String
被评估文本。可以使用 | 划分成多个分支
eval_mode
Integer
评估模式。6:句子多分支评测模式
请求示例
# 参数示例为websocket连接URL展开, 如:soe.cloud.tencent.com/soe/api/1306***?eval_mode=0&voice_format=1&...
server_engine_type=16k_zh
eval_mode=6
ref_text="我有一个苹果 | 我有一个香蕉 | 我有一个梨"
score_coeff=1.000000
voice_format=1

返回结果

主要返回结果说明:
参数名称
类型
描述
SuggestedScore
Float
建议评分
PronAccuracy
Float
整体精准度
PronFluency
Float
整体流利度
PronCompletion
Float
整体完整度
Words.PronAccuracy
Float
单词精准度
Words.PronFluency
Float
单词流利度
Words.MatchTag
Integer
当前词的音频与文本的匹配情况
Words.PhoneInfos.PronAccuracy
Float
音素精准度
Words.PhoneInfos.MatchTag
Integer
当前音素的音频与文本的匹配情况
请求示例
{ "code": 0, "message": "2efd8547-a3b1-4ab5-9b51-526778ae552c_7", "voice_id": "2efd8547-a3b1-4ab5-9b51-526778ae552c", "result": { "SuggestedScore": 98.72620391845703, "PronAccuracy": 98.72620391845703, "PronFluency": 0.9929763674736023, "PronCompletion": 1, "Words": [ { "MemBeginTime": 200, "MemEndTime": 330, "PronAccuracy": 98.37909698486328, "PronFluency": 1, "ReferenceWord": "", "Word": "我", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 200, "MemEndTime": 250, "PronAccuracy": 98.41050720214844, "DetectedStress": false, "Phone": "w", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 250, "MemEndTime": 330, "PronAccuracy": 98.36338806152344, "DetectedStress": false, "Phone": "o3", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } }, { "MemBeginTime": 330, "MemEndTime": 480, "PronAccuracy": 98.68958282470703, "PronFluency": 0.9998577237129211, "ReferenceWord": "", "Word": "有", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 330, "MemEndTime": 390, "PronAccuracy": 99.25726318359375, "DetectedStress": false, "Phone": "y", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 390, "MemEndTime": 480, "PronAccuracy": 98.5003662109375, "DetectedStress": false, "Phone": "iu3", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } }, { "MemBeginTime": 480, "MemEndTime": 540, "PronAccuracy": 98.76148223876953, "PronFluency": 1, "ReferenceWord": "", "Word": "一", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 480, "MemEndTime": 510, "PronAccuracy": 98.57884216308594, "DetectedStress": false, "Phone": "y", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 510, "MemEndTime": 540, "PronAccuracy": 98.94412231445312, "DetectedStress": false, "Phone": "i2", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } }, { "MemBeginTime": 540, "MemEndTime": 630, "PronAccuracy": 99.01979064941406, "PronFluency": 1, "ReferenceWord": "", "Word": "个", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 540, "MemEndTime": 580, "PronAccuracy": 98.98639678955078, "DetectedStress": false, "Phone": "g", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 580, "MemEndTime": 630, "PronAccuracy": 99.05318450927734, "DetectedStress": false, "Phone": "e4", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } }, { "MemBeginTime": 630, "MemEndTime": 880, "PronAccuracy": 98.79436492919922, "PronFluency": 0.9961593747138977, "ReferenceWord": "", "Word": "苹", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 630, "MemEndTime": 710, "PronAccuracy": 99.29827880859375, "DetectedStress": false, "Phone": "p", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 710, "MemEndTime": 880, "PronAccuracy": 98.54241180419922, "DetectedStress": false, "Phone": "ing2", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } }, { "MemBeginTime": 880, "MemEndTime": 1250, "PronAccuracy": 98.83470916748047, "PronFluency": 0.9618411064147949, "ReferenceWord": "", "Word": "果", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 880, "MemEndTime": 950, "PronAccuracy": 98.8805923461914, "DetectedStress": false, "Phone": "g", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 950, "MemEndTime": 1250, "PronAccuracy": 98.81178283691406, "DetectedStress": false, "Phone": "uo3", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } } ], "SentenceId": 0, "RefTextId": 0, "KeyWordHits": null, "UnKeyWordHits": null }, "final": 1 }

指定发音

使用 汉字{::pron{p1,p2..},{p3,p4..}..} 指定发音,发音单元为 拼音

请求参数

主要请求参数说明:
参数名称
类型
描述
ref_text
String
被评估文本
eval_mode
Integer
评估模式。6:句子多分支评测模式
请求示例
# 参数示例为websocket连接URL展开, 如:soe.cloud.tencent.com/soe/api/1306***?eval_mode=0&voice_format=1&...
server_engine_type=16k_zh
eval_mode=6
ref_text="清平乐{::pron{yue4}}"
score_coeff=1.000000
voice_format=1

返回结果

主要返回结果说明:
参数名称
类型
描述
SuggestedScore
Float
建议评分
PronAccuracy
Float
整体精准度
PronFluency
Float
整体流利度
Words.PronAccuracy
Float
单词精准度
Words.PronFluency
Float
单词流利度
Words.PhoneInfos.PronAccuracy
Float
音素精准度
返回示例
返回类似相应案例 段落评测模式