Merge pull request #120 from hepower/master

szhaomsft · web-flow · commit 6197ab501197 · 2019-08-01T17:42:36.000+08:00
Update client to:
diff --git a/CustomVoice-API-Samples/CSharp/CustomVoice-API/CustomVoiceAPI.cs b/CustomVoice-API-Samples/CSharp/CustomVoice-API/CustomVoiceAPI.cs
@@ -230,16 +230,15 @@ public void UpdateSynthesis(Guid id, string newName, string newDesc)
             VoiceAPIHelper.PatchVoiceSynthesis(VoiceSynthesisUpdate.Create(newName, newDesc), this.subscriptionKey, string.Format(CultureInfo.InvariantCulture, DeleteSynthesisUrl, id.ToString()));
         }
 
-        public async Task<Uri> CreateVoiceSynthesis(string name, string description, string locale, string inputTextPath, Guid modelId, bool concatenateResult)
+        public async Task<Uri> CreateVoiceSynthesis(string name, string description, string locale, string outputFormat, string inputTextPath, IEnumerable<Guid> modelIds, bool concatenateResult)
         {
             Console.WriteLine("Creating batch synthesiss.");
             var properties = new Dictionary<string, string>();
             if (concatenateResult)
             {
                 properties.Add("ConcatenateResult", "true");
             }
-            var model = ModelIdentity.Create(modelId);
-            var voiceSynthesisDefinition = VoiceSynthesisDefinition.Create(name, description, locale, model, properties);
+            var voiceSynthesisDefinition = VoiceSynthesisDefinition.Create(name, description, locale, outputFormat, modelIds, properties);
             using (var submitResponse = VoiceAPIHelper.SubmitVoiceSynthesis(voiceSynthesisDefinition, inputTextPath, VoiceSynthesisUrl, this.subscriptionKey))
             {
                 return await GetLocationFromPostResponseAsync(submitResponse).ConfigureAwait(false);
diff --git a/CustomVoice-API-Samples/CSharp/CustomVoice-API/Program.cs b/CustomVoice-API-Samples/CSharp/CustomVoice-API/Program.cs
@@ -127,11 +127,28 @@ private static async Task VoiceSynthsisAPIs()
                 return;
             }
 
+            List<Guid> modelIds = new List<Guid>();
+            modelIds.Add(voiceId);
+
             // indicate if want concatenate the output waves with a single file or not.
-            bool concatenateResult = true;
+            bool concatenateResult = false;
+
+            string outputFormat = "riff-16khz-16bit-mono-pcm";
+            /* Available output format:
+            "riff-8khz-16bit-mono-pcm",
+            "riff-16khz-16bit-mono-pcm",
+            "riff-24khz-16bit-mono-pcm",
+            "riff-48khz-16bit-mono-pcm",
+            "audio-16khz-32kbitrate-mono-mp3",
+            "audio-16khz-64kbitrate-mono-mp3",
+            "audio-16khz-128kbitrate-mono-mp3",
+            "audio-24khz-48kbitrate-mono-mp3",
+            "audio-24khz-96kbitrate-mono-mp3",
+            "audio-24khz-160kbitrate-mono-mp3",
+            */
 
             // Submit a voice synthesis request and get a ID
-            var synthesisLocation = await customVoiceAPI.CreateVoiceSynthesis(name, description, locale, localInputTextFile, voiceId, concatenateResult).ConfigureAwait(false);
+            var synthesisLocation = await customVoiceAPI.CreateVoiceSynthesis(name, description, locale, outputFormat, localInputTextFile, modelIds, concatenateResult).ConfigureAwait(false);
             var synthesisId = new Guid(synthesisLocation.ToString().Split('/').LastOrDefault());
 
             Console.WriteLine("Checking status.");
@@ -199,11 +216,11 @@ private static Guid GetVoiceId(CustomVoiceAPI api, string locale, string voiceNa
             Voice voice = null;
             if (publicVoice)
             {
-                voice = voices.Where(m => m.Locale == locale && m.Name.Contains(voiceName) && m.IsPublicVoice).FirstOrDefault();
+                voice = voices.Where(m => m.Locale == locale && m.Name.Contains(voiceName) && m.IsPublicVoice).OrderByDescending(m => m.Created).FirstOrDefault();
             }
             else
             {
-                voice = voices.Where(m => m.Locale == locale && m.Name.Contains(voiceName)).FirstOrDefault();
+                voice = voices.Where(m => m.Locale == locale && m.Name.Contains(voiceName)).OrderByDescending(m => m.Created).FirstOrDefault();
             }
             if (voice == null)
             {
diff --git a/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/DTO/Voice.cs b/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/DTO/Voice.cs
@@ -10,17 +10,21 @@ namespace Microsoft.SpeechServices.Cris.Http
     public sealed class Voice
     {
         [JsonConstructor]
-        private Voice(Guid id, string name, string locale, string gender, bool isPublicVoice)
+        private Voice(Guid id, string name, string description, string locale, string gender, bool isPublicVoice, DateTime created)
         {
             this.Id = id;
             this.Name = name;
+            this.Description = description;
             this.Gender = gender;
             this.Locale = locale;
             this.IsPublicVoice = isPublicVoice;
+            this.Created = created;
         }
 
         public string Name { get; set; }
 
+        public string Description { get; set; }
+
 
         public string Locale { get; set; }
 
@@ -31,5 +35,7 @@ private Voice(Guid id, string name, string locale, string gender, bool isPublicV
         public string Gender { get; set; }
 
         public bool IsPublicVoice { get; set; }
+
+        public DateTime Created { get; set; }
     }
 }
diff --git a/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/DTO/VoiceSynthesisDefinition.cs b/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/DTO/VoiceSynthesisDefinition.cs
@@ -9,12 +9,13 @@ namespace Microsoft.SpeechServices.Cris.Http
 
     public sealed class VoiceSynthesisDefinition
     {
-        private VoiceSynthesisDefinition(string name, string description, string locale, ModelIdentity model, IReadOnlyDictionary<string, string> properties)
+        private VoiceSynthesisDefinition(string name, string description, string locale, string outputFormat, IEnumerable<Guid> models, IReadOnlyDictionary<string, string> properties)
         {
             this.Name = name;
             this.Description = description;
             this.Locale = locale;
-            this.Model = model;
+            this.OutputFormat = outputFormat;
+            this.Models = models;
             this.Properties = properties;
         }
 
@@ -26,18 +27,21 @@ private VoiceSynthesisDefinition(string name, string description, string locale,
 
         public string Locale { get; set; }
 
-        public ModelIdentity Model { get; set; }
+        public string OutputFormat { get; set; }
+
+        public IEnumerable<Guid> Models { get; set; }
 
         public IReadOnlyDictionary<string, string> Properties { get; set; }
 
         public static VoiceSynthesisDefinition Create(
             string name,
             string description,
             string locale,
-            ModelIdentity model,
+            string outputFormat,
+            IEnumerable<Guid> models,
             IReadOnlyDictionary<string, string> properties)
         {
-            return new VoiceSynthesisDefinition(name, description, locale, model, properties);
+            return new VoiceSynthesisDefinition(name, description, locale, outputFormat, models, properties);
         }
     }
 }
diff --git a/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/VoiceAPIHelper.cs b/CustomVoice-API-Samples/CSharp/CustomVoice-API/VoiceAPI/VoiceAPIHelper.cs
@@ -174,9 +174,14 @@ public static HttpResponseMessage SubmitVoiceSynthesis(VoiceSynthesisDefinition
                     content.Add(new StringContent(voiceSynthesisDefinition.Description), "description");
                 }
 
-                content.Add(new StringContent(voiceSynthesisDefinition.Model.Id.ToString()), "model");
+                content.Add(new StringContent(JsonConvert.SerializeObject(voiceSynthesisDefinition.Models)), "models");
                 content.Add(new StringContent(voiceSynthesisDefinition.Locale), "locale");
 
+                if (!string.IsNullOrEmpty(voiceSynthesisDefinition.OutputFormat))
+                {
+                    content.Add(new StringContent(voiceSynthesisDefinition.OutputFormat), "outputformat");
+                }
+
                 if (voiceSynthesisDefinition.Properties != null)
                 {
                     content.Add(new StringContent(JsonConvert.SerializeObject(voiceSynthesisDefinition.Properties)), "properties");
diff --git a/CustomVoice-API-Samples/Python/Readme.txt b/CustomVoice-API-Samples/Python/Readme.txt
@@ -1,20 +1,31 @@
-1. Install Python2 from https://www.python.org/downloads/release/python-2716/
+1. Install Python from https://www.python.org/downloads/release/
 
 Usage guide:
 
 1.Check the help of the tool:
-C:\Python27amd64\python.exe voiceclient.py -h
+python voiceclient.py -h
 
 2.Get available voice list:
-C:\Python27amd64\python.exe voiceclient.py --voices -region centralindia -key your_key_here
+python voiceclient.py --voices -region centralindia -key your_key_here
 
 3.Submit a voice synthesis request:
-C:\Python27amd64\python.exe voiceclient.py --submit -region centralindia -key your_key_here-file zh-CN.txt -locale zh-CN -voiceId voice_id_here --concatenateResult
+python voiceclient.py --submit -region centralindia -key your_key_here -file zh-CN.txt -locale zh-CN -voiceId voice_id_here -format riff-16khz-16bit-mono-pcm --concatenateResult
 
 Note:
 a.The input text file should be Unicode format with 'UTF-8-BOM' (you can check the text format with Notepad++), like the one zh-CN.txt, and should be more than 50 lines.
 b.The voiceId should pick up from MS guys or get from step2 above.
-c.'concatenateResult' is a optional parameters, if not give, the output will be multiple wave files per each line.
+c Available audio output formats are:
+	"riff-8khz-16bit-mono-pcm",
+	"riff-16khz-16bit-mono-pcm",
+	"riff-24khz-16bit-mono-pcm",
+	"riff-48khz-16bit-mono-pcm",
+	"audio-16khz-32kbitrate-mono-mp3",
+	"audio-16khz-64kbitrate-mono-mp3",
+	"audio-16khz-128kbitrate-mono-mp3",
+	"audio-24khz-48kbitrate-mono-mp3",
+	"audio-24khz-96kbitrate-mono-mp3",
+	"audio-24khz-160kbitrate-mono-mp3",
+d.'concatenateResult' is a optional parameters, if not give, the output will be multiple wave files per each line.
 
 
 
diff --git a/CustomVoice-API-Samples/Python/voiceclient.py b/CustomVoice-API-Samples/Python/voiceclient.py
@@ -16,16 +16,16 @@
 parser.add_argument('--submit', action="store_true", default=False, help='submit a synthesis request')
 parser.add_argument('--concatenateResult', action="store_true", default=False, help='If concatenate result in a single wave file')
 parser.add_argument('-file', action="store",  dest="file", help='the input text file path')
-parser.add_argument('-voiceId', action="store", dest="voiceId", help='the id of the voice which used to synthesis')
+parser.add_argument('-voiceId', action="store", nargs='+', dest="voiceId", help='the id of the voice which used to synthesis')
 parser.add_argument('-locale', action="store", dest="locale", help='the locale information like zh-CN/en-US')
+parser.add_argument('-format', action="store", dest="format", default='riff-16khz-16bit-mono-pcm', help='the output audio format')
 parser.add_argument('-key', action="store", dest="key", required=True, help='the cris subscription key, like ff1eb62d06d34767bda0207acb1da7d7 ')
 parser.add_argument('-region', action="store", dest="region", required=True, help='the region information, could be centralindia, canadacentral or uksouth')
 
 args = parser.parse_args()
 
 baseAddress = 'https://%s.cris.ai/api/texttospeech/v3.0-beta1/' % args.region
 
-
 def getSubmittedSyntheses():
     response=requests.get(baseAddress+"voicesynthesis", headers={"Ocp-Apim-Subscription-Key":args.key}, verify=False)
     syntheses = json.loads(response.text)
@@ -43,8 +43,9 @@ def getVoices():
 
 
 def submitSynthesis():
-    filename=ntpath.basename(args.file)        
-    data={'name': 'simple test', 'description': 'desc...', 'model': args.voiceId, 'locale': args.locale}
+    filename=ntpath.basename(args.file)
+    modelList = args.voiceId
+    data={'name': 'simple test', 'description': 'desc...', 'models': json.dumps(modelList), 'locale': args.locale, 'outputformat': args.format}
     if args.concatenateResult:
         properties={'ConcatenateResult': 'true'}
         data['properties'] = json.dumps(properties)
@@ -57,19 +58,21 @@ def submitSynthesis():
         return id
     else:
         print("Submit synthesis request failed")
+        print("response.status_code: %d" % response.status_code)
+        print("response.text: %s" % response.text)
         return 0
 
 if args.voices:
     voices = getVoices()
     print("There are %d voices available:" % len(voices))
     for voice in voices:
-        print ("Name: %s, Id: %s, Locale: %s, Gender: %s, PublicVoice: %s" % (voice['name'], voice['id'], voice['locale'], voice['gender'], voice['isPublicVoice']))
+        print ("Name: %s, Description: %s, Id: %s, Locale: %s, Gender: %s, PublicVoice: %s, Created: %s" % (voice['name'], voice['description'], voice['id'], voice['locale'], voice['gender'], voice['isPublicVoice'], voice['created']))
 
 if args.syntheses:
     synthese = getSubmittedSyntheses()
     print("There are %d synthesis requests submitted:" % len(synthese))
     for synthesis in synthese:
-        print synthesis['name']
+        print (synthesis['name'])
 
 if args.submit:
     id = submitSynthesis()
@@ -86,6 +89,9 @@ def submitSynthesis():
                 f.write(r.content)
                 print("Succeeded... Result file downloaded : " + filename)
             break
+        elif synthesis['status'] == "Failed":
+            print("Failed...")
+            break
         elif synthesis['status'] == "Running":
             print("Running...")
         elif synthesis['status'] == "NotStarted":

Original file line number	Diff line number	Diff line change
`@@ -230,16 +230,15 @@ public void UpdateSynthesis(Guid id, string newName, string newDesc)`
`230`	`230`	`VoiceAPIHelper.PatchVoiceSynthesis(VoiceSynthesisUpdate.Create(newName, newDesc), this.subscriptionKey, string.Format(CultureInfo.InvariantCulture, DeleteSynthesisUrl, id.ToString()));`
`231`	`231`	`}`
`232`	`232`
`233`		`- public async Task<Uri> CreateVoiceSynthesis(string name, string description, string locale, string inputTextPath, Guid modelId, bool concatenateResult)`
	`233`	`+ public async Task<Uri> CreateVoiceSynthesis(string name, string description, string locale, string outputFormat, string inputTextPath, IEnumerable<Guid> modelIds, bool concatenateResult)`
`234`	`234`	`{`
`235`	`235`	`Console.WriteLine("Creating batch synthesiss.");`
`236`	`236`	`var properties = new Dictionary<string, string>();`
`237`	`237`	`if (concatenateResult)`
`238`	`238`	`{`
`239`	`239`	`properties.Add("ConcatenateResult", "true");`
`240`	`240`	`}`
`241`		`- var model = ModelIdentity.Create(modelId);`
`242`		`- var voiceSynthesisDefinition = VoiceSynthesisDefinition.Create(name, description, locale, model, properties);`
	`241`	`+ var voiceSynthesisDefinition = VoiceSynthesisDefinition.Create(name, description, locale, outputFormat, modelIds, properties);`
`243`	`242`	`using (var submitResponse = VoiceAPIHelper.SubmitVoiceSynthesis(voiceSynthesisDefinition, inputTextPath, VoiceSynthesisUrl, this.subscriptionKey))`
`244`	`243`	`{`
`245`	`244`	`return await GetLocationFromPostResponseAsync(submitResponse).ConfigureAwait(false);`
Original file line number	Diff line number	Diff line change
`@@ -10,17 +10,21 @@ namespace Microsoft.SpeechServices.Cris.Http`
`10`	`10`	`public sealed class Voice`
`11`	`11`	`{`
`12`	`12`	`[JsonConstructor]`
`13`		`- private Voice(Guid id, string name, string locale, string gender, bool isPublicVoice)`
	`13`	`+ private Voice(Guid id, string name, string description, string locale, string gender, bool isPublicVoice, DateTime created)`
`14`	`14`	`{`
`15`	`15`	`this.Id = id;`
`16`	`16`	`this.Name = name;`
	`17`	`+ this.Description = description;`
`17`	`18`	`this.Gender = gender;`
`18`	`19`	`this.Locale = locale;`
`19`	`20`	`this.IsPublicVoice = isPublicVoice;`
	`21`	`+ this.Created = created;`
`20`	`22`	`}`
`21`	`23`
`22`	`24`	`public string Name { get; set; }`
`23`	`25`
	`26`	`+ public string Description { get; set; }`
	`27`	`+`
`24`	`28`
`25`	`29`	`public string Locale { get; set; }`
`26`	`30`
`@@ -31,5 +35,7 @@ private Voice(Guid id, string name, string locale, string gender, bool isPublicV`
`31`	`35`	`public string Gender { get; set; }`
`32`	`36`
`33`	`37`	`public bool IsPublicVoice { get; set; }`
	`38`	`+`
	`39`	`+ public DateTime Created { get; set; }`
`34`	`40`	`}`
`35`	`41`	`}`
Original file line number	Diff line number	Diff line change
`@@ -9,12 +9,13 @@ namespace Microsoft.SpeechServices.Cris.Http`
`9`	`9`
`10`	`10`	`public sealed class VoiceSynthesisDefinition`
`11`	`11`	`{`
`12`		`- private VoiceSynthesisDefinition(string name, string description, string locale, ModelIdentity model, IReadOnlyDictionary<string, string> properties)`
	`12`	`+ private VoiceSynthesisDefinition(string name, string description, string locale, string outputFormat, IEnumerable<Guid> models, IReadOnlyDictionary<string, string> properties)`
`13`	`13`	`{`
`14`	`14`	`this.Name = name;`
`15`	`15`	`this.Description = description;`
`16`	`16`	`this.Locale = locale;`
`17`		`- this.Model = model;`
	`17`	`+ this.OutputFormat = outputFormat;`
	`18`	`+ this.Models = models;`
`18`	`19`	`this.Properties = properties;`
`19`	`20`	`}`
`20`	`21`
`@@ -26,18 +27,21 @@ private VoiceSynthesisDefinition(string name, string description, string locale,`
`26`	`27`
`27`	`28`	`public string Locale { get; set; }`
`28`	`29`
`29`		`- public ModelIdentity Model { get; set; }`
	`30`	`+ public string OutputFormat { get; set; }`
	`31`	`+`
	`32`	`+ public IEnumerable<Guid> Models { get; set; }`
`30`	`33`
`31`	`34`	`public IReadOnlyDictionary<string, string> Properties { get; set; }`
`32`	`35`
`33`	`36`	`public static VoiceSynthesisDefinition Create(`
`34`	`37`	`string name,`
`35`	`38`	`string description,`
`36`	`39`	`string locale,`
`37`		`- ModelIdentity model,`
	`40`	`+ string outputFormat,`
	`41`	`+ IEnumerable<Guid> models,`
`38`	`42`	`IReadOnlyDictionary<string, string> properties)`
`39`	`43`	`{`
`40`		`- return new VoiceSynthesisDefinition(name, description, locale, model, properties);`
	`44`	`+ return new VoiceSynthesisDefinition(name, description, locale, outputFormat, models, properties);`
`41`	`45`	`}`
`42`	`46`	`}`
`43`	`47`	`}`
Original file line number	Diff line number	Diff line change
`@@ -174,9 +174,14 @@ public static HttpResponseMessage SubmitVoiceSynthesis(VoiceSynthesisDefinition`
`174`	`174`	`content.Add(new StringContent(voiceSynthesisDefinition.Description), "description");`
`175`	`175`	`}`
`176`	`176`
`177`		`- content.Add(new StringContent(voiceSynthesisDefinition.Model.Id.ToString()), "model");`
	`177`	`+ content.Add(new StringContent(JsonConvert.SerializeObject(voiceSynthesisDefinition.Models)), "models");`
`178`	`178`	`content.Add(new StringContent(voiceSynthesisDefinition.Locale), "locale");`
`179`	`179`
	`180`	`+ if (!string.IsNullOrEmpty(voiceSynthesisDefinition.OutputFormat))`
	`181`	`+ {`
	`182`	`+ content.Add(new StringContent(voiceSynthesisDefinition.OutputFormat), "outputformat");`
	`183`	`+ }`
	`184`	`+`
`180`	`185`	`if (voiceSynthesisDefinition.Properties != null)`
`181`	`186`	`{`
`182`	`187`	`content.Add(new StringContent(JsonConvert.SerializeObject(voiceSynthesisDefinition.Properties)), "properties");`