tencentcloud-sdk-asr 3.0.657 → 3.0.659
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/VERSION +1 -1
- data/lib/v20190614/models.rb +114 -60
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 837bbe0904be82a09c8dc1834cd40f5eb5da0f82
|
4
|
+
data.tar.gz: 64967529ada2b02c6803727492215094538972ac
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5dc9e0fb5cb69aaf329f50db89f06320547958055a190038adc954aa69864cbe7b95896e07ddca70b4ae9508fa4e24be7c1460c7d224e622c8e6a20413055ced
|
7
|
+
data.tar.gz: 75b9ff344c6b327c6dd7e687b94147536c4d7769bd9a0a072c2b8189a0ba55a1bc9b9b097a191b44bfd5d7206eaa13d0a624b16e52a4587fb1fe478f5ae58b67
|
data/lib/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
3.0.
|
1
|
+
3.0.659
|
data/lib/v20190614/models.rb
CHANGED
@@ -295,7 +295,7 @@ module TencentCloud
|
|
295
295
|
# **注意:电话通讯场景,请务必使用以下8k引擎**
|
296
296
|
# • 8k_zh:中文电话通讯;
|
297
297
|
# • 8k_en:英文电话通讯;
|
298
|
-
# 如您有电话通讯场景识别需求,但发现需求语种仅支持16k,可将8k音频传入下方16k引擎,亦能获取识别结果。但**16k
|
298
|
+
# 如您有电话通讯场景识别需求,但发现需求语种仅支持16k,可将8k音频传入下方16k引擎,亦能获取识别结果。但**16k引擎并非基于电话通讯数据训练,无法承诺此种调用方式的识别效果,需由您自行验证识别结果是否可用**
|
299
299
|
|
300
300
|
# 通用场景引擎:
|
301
301
|
# **注意:除电话通讯场景以外的其它识别场景,请务必使用以下16k引擎**
|
@@ -323,23 +323,46 @@ module TencentCloud
|
|
323
323
|
# 2:双声道(仅支持8k电话音频,且双声道应分别为通话双方)
|
324
324
|
|
325
325
|
# 注意:
|
326
|
-
# • 16k音频:仅支持单声道识别,**需设置ChannelNum=1
|
326
|
+
# • 16k音频:仅支持单声道识别,**需设置ChannelNum=1**;
|
327
327
|
# • 8k电话音频:支持单声道、双声道识别,**建议设置ChannelNum=2,即双声道**。双声道能够物理区分说话人、避免说话双方重叠产生的识别错误,能达到最好的说话人分离效果和识别效果。设置双声道后,将自动区分说话人,因此**无需再开启说话人分离功能**,相关参数(**SpeakerDiarization、SpeakerNumber**)使用默认值即可
|
328
328
|
# @type ChannelNum: Integer
|
329
|
-
# @param ResTextFormat:
|
330
|
-
# 0
|
331
|
-
# 1
|
332
|
-
# 2
|
333
|
-
# 3
|
334
|
-
# 4
|
329
|
+
# @param ResTextFormat: 识别结果返回样式
|
330
|
+
# 0:基础识别结果(仅包含有效人声时间戳,无词粒度的[详细识别结果](https://cloud.tencent.com/document/api/1093/37824#SentenceDetail));
|
331
|
+
# 1:基础识别结果之上,增加词粒度的[详细识别结果](https://cloud.tencent.com/document/api/1093/37824#SentenceDetail)(包含词级别时间戳、语速值,**不含标点**);
|
332
|
+
# 2:基础识别结果之上,增加词粒度的[详细识别结果](https://cloud.tencent.com/document/api/1093/37824#SentenceDetail)(包含词级别时间戳、语速值和标点);
|
333
|
+
# 3:基础识别结果之上,增加词粒度的[详细识别结果](https://cloud.tencent.com/document/api/1093/37824#SentenceDetail)(包含词级别时间戳、语速值和标点),且识别结果按标点符号分段,**适用字幕场景**;
|
334
|
+
# 4:**【增值付费功能】**基础识别结果之上,增加词粒度的[详细识别结果](https://cloud.tencent.com/document/api/1093/37824#SentenceDetail)(包含词级别时间戳、语速值和标点),且识别结果按nlp语义分段,**适用会议、庭审记录转写等场景**,仅支持8k_zh/16k_zh引擎
|
335
|
+
|
336
|
+
# 注意:如果传入参数值4,需确保账号已购买[语义分段资源包](https://cloud.tencent.com/document/product/1093/35686#97ae4aa0-29a0-4066-9f07-ccaf8856a16b),或账号开启后付费;**若当前账号已开启后付费功能,并传入参数值4,将[自动计费](https://cloud.tencent.com/document/product/1093/35686#d912167d-ffd5-41a9-8b1c-2e89845a6852))**
|
335
337
|
# @type ResTextFormat: Integer
|
336
338
|
# @param SourceType: 语音数据来源
|
337
339
|
# 0:语音 URL;
|
338
340
|
# 1:语音数据(post body)
|
339
341
|
# @type SourceType: Integer
|
342
|
+
# @param Data: 语音数据base64编码
|
343
|
+
# **当 SourceType 值为 1 时须填写该字段,为 0 时不需要填写**
|
344
|
+
|
345
|
+
# 注意:音频数据要小于5MB(含)
|
346
|
+
# @type Data: String
|
347
|
+
# @param DataLen: 数据长度(此数据长度为数据未进行base64编码时的长度)
|
348
|
+
# @type DataLen: Integer
|
349
|
+
# @param Url: 语音URL的地址(需要公网环境浏览器可下载)
|
350
|
+
# **当 SourceType 值为 0 时须填写该字段,为 1 时不需要填写**
|
351
|
+
|
352
|
+
# 注意:
|
353
|
+
# 1. 请确保录音文件时长在5个小时(含)之内,否则可能识别失败;
|
354
|
+
# 2. 请保证文件的下载速度,否则可能下载失败
|
355
|
+
# @type Url: String
|
356
|
+
# @param CallbackUrl: 回调 URL
|
357
|
+
# 用户自行搭建的用于接收识别结果的服务URL
|
358
|
+
# 回调格式和内容详见:[录音识别回调说明](https://cloud.tencent.com/document/product/1093/52632)
|
359
|
+
|
360
|
+
# 注意:
|
361
|
+
# 如果用户使用轮询方式获取识别结果,则无需提交该参数
|
362
|
+
# @type CallbackUrl: String
|
340
363
|
# @param SpeakerDiarization: 是否开启说话人分离
|
341
364
|
# 0:不开启;
|
342
|
-
# 1
|
365
|
+
# 1:开启(仅支持以下引擎:8k_zh/16k_zh/16k_ms/16k_en/16k_id,且ChannelNum=1时可用);
|
343
366
|
# 默认值为 0
|
344
367
|
|
345
368
|
# 注意:
|
@@ -350,66 +373,97 @@ module TencentCloud
|
|
350
373
|
# 0:自动分离(最多分离出20个人);
|
351
374
|
# 1-10:指定人数分离;
|
352
375
|
# 默认值为 0
|
353
|
-
|
354
|
-
# 注意:此功能结果仅供参考
|
355
376
|
# @type SpeakerNumber: Integer
|
356
|
-
# @param
|
357
|
-
#
|
358
|
-
#
|
359
|
-
#
|
360
|
-
# @type Url: String
|
361
|
-
# @param Data: 语音数据base64编码,当SourceType 值为1时必须填写,为0可不写。音频数据要小于5MB。
|
362
|
-
# @type Data: String
|
363
|
-
# @param DataLen: 数据长度,非必填(此数据长度为数据未进行base64编码时的数据长度)。
|
364
|
-
# @type DataLen: Integer
|
365
|
-
# @param ConvertNumMode: 是否进行阿拉伯数字智能转换(目前支持中文普通话引擎)。0:不转换,直接输出中文数字,1:根据场景智能转换为阿拉伯数字,3: 打开数学相关数字转换。默认值为 1。
|
366
|
-
# @type ConvertNumMode: Integer
|
367
|
-
# @param FilterDirty: 是否过滤脏词(目前支持中文普通话引擎)。0:不过滤脏词;1:过滤脏词;2:将脏词替换为 * 。默认值为 0。
|
368
|
-
# @type FilterDirty: Integer
|
369
|
-
# @param HotwordId: 热词表id。如不设置该参数,自动生效默认热词表;如设置了该参数,那么将生效对应的热词表。
|
377
|
+
# @param HotwordId: 热词表id
|
378
|
+
# 如不设置该参数,将自动生效默认热词表;
|
379
|
+
# 如设置该参数,将生效对应id的热词表;
|
380
|
+
# 点击这里查看[热词表配置方法](https://cloud.tencent.com/document/product/1093/40996)
|
370
381
|
# @type HotwordId: String
|
371
|
-
# @param
|
382
|
+
# @param ReinforceHotword: 热词增强功能(目前仅支持8k_zh/16k_zh引擎)
|
383
|
+
# 1:开启热词增强功能
|
384
|
+
|
385
|
+
# 注意:热词增强功能开启后,将对传入的热词表id开启同音替换功能,可以在这里查看[热词表配置方法](https://cloud.tencent.com/document/product/1093/40996)。效果举例:在热词表中配置“蜜制”一词,并开启增强功能,与“蜜制”(mìzhì)同音同调的“秘制”(mìzhì)的识别结果会被强制替换成“蜜制”。**建议客户根据实际的业务需求开启该功能**
|
386
|
+
# @type ReinforceHotword: Integer
|
387
|
+
# @param CustomizationId: 自学习定制模型 id
|
388
|
+
# 如设置了该参数,将生效对应id的自学习定制模型;
|
389
|
+
# 点击这里查看[自学习定制模型配置方法](https://cloud.tencent.com/document/product/1093/38416)
|
372
390
|
# @type CustomizationId: String
|
373
|
-
# @param
|
374
|
-
#
|
375
|
-
#
|
391
|
+
# @param EmotionRecognition: **【增值付费功能】**情绪识别能力(目前仅支持16k_zh)
|
392
|
+
# 0:不开启;
|
393
|
+
# 1:开启情绪识别,但不在文本展示情绪标签;
|
394
|
+
# 2:开启情绪识别,并且在文本展示情绪标签(**该功能需要设置ResTextFormat 大于0**)
|
395
|
+
# 默认值为0
|
396
|
+
# 支持的情绪分类为:高兴、伤心、愤怒
|
397
|
+
|
398
|
+
# 注意:
|
399
|
+
# 1. **本功能为增值服务**,需将参数设置为1或2时方可按对应方式生效;
|
400
|
+
# 2. 如果传入参数值1或2,需确保账号已购买[情绪识别资源包](https://cloud.tencent.com/document/product/1093/35686#97ae4aa0-29a0-4066-9f07-ccaf8856a16b),或账号开启后付费;**若当前账号已开启后付费功能,并传入参数值1或2,将[自动计费](https://cloud.tencent.com/document/product/1093/35686#d912167d-ffd5-41a9-8b1c-2e89845a6852))**;
|
401
|
+
# 3. 参数设置为0时,无需购买资源包,也不会消耗情绪识别对应资源
|
402
|
+
# @type EmotionRecognition: Integer
|
403
|
+
# @param EmotionalEnergy: 情绪能量值
|
404
|
+
# 取值为音量分贝值/10,取值范围:[1,10],值越高情绪越强烈
|
405
|
+
# 0:不开启;
|
406
|
+
# 1:开启;
|
407
|
+
# 默认值为0
|
408
|
+
# @type EmotionalEnergy: Integer
|
409
|
+
# @param ConvertNumMode: 阿拉伯数字智能转换(目前仅支持8k_zh/16k_zh引擎)
|
410
|
+
# 0:不转换,直接输出中文数字;
|
411
|
+
# 1:根据场景智能转换为阿拉伯数字;
|
412
|
+
# 3:打开数学相关数字转换(如:阿尔法转写为α);
|
413
|
+
# 默认值为 1
|
414
|
+
# @type ConvertNumMode: Integer
|
415
|
+
# @param FilterDirty: 脏词过滤(目前仅支持8k_zh/16k_zh引擎)
|
416
|
+
# 0:不过滤脏词;
|
417
|
+
# 1:过滤脏词;
|
418
|
+
# 2:将脏词替换为 * ;
|
419
|
+
# 默认值为 0
|
420
|
+
# @type FilterDirty: Integer
|
421
|
+
# @param FilterPunc: 标点符号过滤(目前仅支持8k_zh/16k_zh引擎)
|
422
|
+
# 0:不过滤标点;
|
423
|
+
# 1:过滤句末标点;
|
424
|
+
# 2:过滤所有标点;
|
425
|
+
# 默认值为 0
|
376
426
|
# @type FilterPunc: Integer
|
377
|
-
# @param FilterModal:
|
427
|
+
# @param FilterModal: 语气词过滤(目前仅支持8k_zh/16k_zh引擎)
|
428
|
+
# 0:不过滤语气词;
|
429
|
+
# 1:过滤部分语气词;
|
430
|
+
# 2:严格过滤语气词;
|
431
|
+
# 默认值为 0
|
378
432
|
# @type FilterModal: Integer
|
379
|
-
# @param
|
380
|
-
#
|
381
|
-
#
|
382
|
-
#
|
383
|
-
|
433
|
+
# @param SentenceMaxLength: 单标点最多字数
|
434
|
+
# **可控制单行字幕最大字数,适用于字幕生成场景**,取值范围:[6,40]
|
435
|
+
# 0:不开启该功能;
|
436
|
+
# 默认值为0
|
437
|
+
|
438
|
+
# 注意:需设置ResTextFormat为3,解析返回的ResultDetail列表,通过结构中FinalSentence获取单个标点断句结果
|
384
439
|
# @type SentenceMaxLength: Integer
|
385
|
-
# @param
|
386
|
-
#
|
387
|
-
# @type EmotionRecognition: Integer
|
440
|
+
# @param Extra: 附加参数**(该参数无意义,忽略即可)**
|
441
|
+
# @type Extra: String
|
388
442
|
|
389
|
-
attr_accessor :EngineModelType, :ChannelNum, :ResTextFormat, :SourceType, :
|
443
|
+
attr_accessor :EngineModelType, :ChannelNum, :ResTextFormat, :SourceType, :Data, :DataLen, :Url, :CallbackUrl, :SpeakerDiarization, :SpeakerNumber, :HotwordId, :ReinforceHotword, :CustomizationId, :EmotionRecognition, :EmotionalEnergy, :ConvertNumMode, :FilterDirty, :FilterPunc, :FilterModal, :SentenceMaxLength, :Extra
|
390
444
|
|
391
|
-
def initialize(enginemodeltype=nil, channelnum=nil, restextformat=nil, sourcetype=nil,
|
445
|
+
def initialize(enginemodeltype=nil, channelnum=nil, restextformat=nil, sourcetype=nil, data=nil, datalen=nil, url=nil, callbackurl=nil, speakerdiarization=nil, speakernumber=nil, hotwordid=nil, reinforcehotword=nil, customizationid=nil, emotionrecognition=nil, emotionalenergy=nil, convertnummode=nil, filterdirty=nil, filterpunc=nil, filtermodal=nil, sentencemaxlength=nil, extra=nil)
|
392
446
|
@EngineModelType = enginemodeltype
|
393
447
|
@ChannelNum = channelnum
|
394
448
|
@ResTextFormat = restextformat
|
395
449
|
@SourceType = sourcetype
|
396
|
-
@SpeakerDiarization = speakerdiarization
|
397
|
-
@SpeakerNumber = speakernumber
|
398
|
-
@CallbackUrl = callbackurl
|
399
|
-
@Url = url
|
400
450
|
@Data = data
|
401
451
|
@DataLen = datalen
|
402
|
-
@
|
403
|
-
@
|
452
|
+
@Url = url
|
453
|
+
@CallbackUrl = callbackurl
|
454
|
+
@SpeakerDiarization = speakerdiarization
|
455
|
+
@SpeakerNumber = speakernumber
|
404
456
|
@HotwordId = hotwordid
|
457
|
+
@ReinforceHotword = reinforcehotword
|
405
458
|
@CustomizationId = customizationid
|
406
|
-
@
|
459
|
+
@EmotionRecognition = emotionrecognition
|
460
|
+
@EmotionalEnergy = emotionalenergy
|
461
|
+
@ConvertNumMode = convertnummode
|
462
|
+
@FilterDirty = filterdirty
|
407
463
|
@FilterPunc = filterpunc
|
408
464
|
@FilterModal = filtermodal
|
409
|
-
@EmotionalEnergy = emotionalenergy
|
410
|
-
@ReinforceHotword = reinforcehotword
|
411
465
|
@SentenceMaxLength = sentencemaxlength
|
412
|
-
@
|
466
|
+
@Extra = extra
|
413
467
|
end
|
414
468
|
|
415
469
|
def deserialize(params)
|
@@ -417,23 +471,23 @@ module TencentCloud
|
|
417
471
|
@ChannelNum = params['ChannelNum']
|
418
472
|
@ResTextFormat = params['ResTextFormat']
|
419
473
|
@SourceType = params['SourceType']
|
420
|
-
@SpeakerDiarization = params['SpeakerDiarization']
|
421
|
-
@SpeakerNumber = params['SpeakerNumber']
|
422
|
-
@CallbackUrl = params['CallbackUrl']
|
423
|
-
@Url = params['Url']
|
424
474
|
@Data = params['Data']
|
425
475
|
@DataLen = params['DataLen']
|
426
|
-
@
|
427
|
-
@
|
476
|
+
@Url = params['Url']
|
477
|
+
@CallbackUrl = params['CallbackUrl']
|
478
|
+
@SpeakerDiarization = params['SpeakerDiarization']
|
479
|
+
@SpeakerNumber = params['SpeakerNumber']
|
428
480
|
@HotwordId = params['HotwordId']
|
481
|
+
@ReinforceHotword = params['ReinforceHotword']
|
429
482
|
@CustomizationId = params['CustomizationId']
|
430
|
-
@
|
483
|
+
@EmotionRecognition = params['EmotionRecognition']
|
484
|
+
@EmotionalEnergy = params['EmotionalEnergy']
|
485
|
+
@ConvertNumMode = params['ConvertNumMode']
|
486
|
+
@FilterDirty = params['FilterDirty']
|
431
487
|
@FilterPunc = params['FilterPunc']
|
432
488
|
@FilterModal = params['FilterModal']
|
433
|
-
@EmotionalEnergy = params['EmotionalEnergy']
|
434
|
-
@ReinforceHotword = params['ReinforceHotword']
|
435
489
|
@SentenceMaxLength = params['SentenceMaxLength']
|
436
|
-
@
|
490
|
+
@Extra = params['Extra']
|
437
491
|
end
|
438
492
|
end
|
439
493
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tencentcloud-sdk-asr
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.0.
|
4
|
+
version: 3.0.659
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Tencent Cloud
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-09-
|
11
|
+
date: 2023-09-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: tencentcloud-sdk-common
|