Merge branch 'develop' v0.2.3

aws-samples · Jun 9, 2022 · 5121f94 · 5121f94
2 parents 385f9b5 + 77d6280
commit 5121f94
Show file tree

Hide file tree

Showing 13 changed files with 123 additions and 332 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.3] - 2022-06-09
+### Fixed
+- Simplifies workflow by using new Transcribe API to specify Custom Vocabulary and Vocabulary Filter at the same time as using Language ID.
+
 ## [0.2.2] - 2022-06-01
 ### Fixed
 - Replaces ':' with '-' when constructing Transcribe job name. Note, use '-' instead of ':' in any custom regex patterns specified in CF parameter, as regex is applied to the generated job name after replacement.
@@ -45,7 +49,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Initial release
 
-[Unreleased]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/compare/v0.2.2...develop
+[Unreleased]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/compare/v0.2.3...develop
+[0.2.3]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/releases/tag/v0.2.3
 [0.2.2]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/releases/tag/v0.2.2
 [0.2.1]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/releases/tag/v0.2.1
 [0.2.0]: https://github.com/aws-samples/amazon-transcribe-post-call-analytics/releases/tag/v0.2.0

diff --git a/System Documentation.pdf b/System Documentation.pdf
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-0.2.2
+0.2.3
diff --git a/pca-main-nokendra.template b/pca-main-nokendra.template
@@ -1,6 +1,6 @@
 AWSTemplateFormatVersion: "2010-09-09"
 
-Description: Amazon Transcribe Post Call Analytics - PCA (v0.2.2) (uksb-1sn29lk73)
+Description: Amazon Transcribe Post Call Analytics - PCA (v0.2.3) (uksb-1sn29lk73)
 
 Parameters:
 

diff --git a/pca-main.template b/pca-main.template
@@ -1,6 +1,6 @@
 AWSTemplateFormatVersion: "2010-09-09"
 
-Description: Amazon Transcribe Post Call Analytics - PCA (v0.2.2) (uksb-1sn29lk73)
+Description: Amazon Transcribe Post Call Analytics - PCA (v0.2.3) (uksb-1sn29lk73)
 
 Parameters:
 

diff --git a/pca-server/cfn/lib/boto3.template b/pca-server/cfn/lib/boto3.template
@@ -90,7 +90,7 @@ Resources:
                   os.mkdir(root_path)
                 # Write out the requirements.txt file, which is the boto3 version we need
                 with open(reqs_file, 'w') as f:
-                  f.write("boto3==1.18.51")
+                  f.write("boto3==1.24.2")
                   f.close()
                 # Install this version of boto3 locally and copy out Transcribe model
                 subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", reqs_file, "-t", pip_folder])

diff --git a/pca-server/cfn/lib/pca-definition.json b/pca-server/cfn/lib/pca-definition.json
@@ -1,19 +1,7 @@
 {
   "Comment": "Post-Call Analytics Workflow with Transcribe and Comprehend",
-  "StartAt": "LanguageDetection?",
+  "StartAt": "TranscribeAudio",
   "States": {
-    "LanguageDetection?": {
-      "Type": "Choice",
-      "Comment": "Triggers Language Detection is required",
-      "Choices": [
-        {
-          "Variable": "$.langCode",
-          "StringEquals": "",
-          "Next": "TranscribeLangDetectClip"
-        }
-      ],
-      "Default": "TranscribeAudio"
-    },
     "TranscribeAudio": {
       "Comment": "Sends the file in S3 for Transcription",
       "Type": "Task",
@@ -24,77 +12,6 @@
       }],
       "Next": "TranscribeStarted?"
     },
-    "TranscribeLangDetectClip": {
-      "Type": "Task",
-      "Resource": "${SFLanguageDetectionArn}",
-      "Retry": [{
-          "IntervalSeconds": 5,
-          "ErrorEquals": ["Lambda.Unknown"]
-      }],
-      "Next": "LanguageDetectPossible?"
-    },
-    "LanguageDetectPossible?": {
-      "Type": "Choice",
-      "Comment": "Checks if we created our language detection job or now",
-      "Choices": [
-        {
-          "Not": {
-            "Variable": "$.langCode",
-            "StringEquals": ""
-          },
-          "Next": "TranscribeAudio"
-        }
-      ],
-      "Default": "WaitForLangDetectTranscribe"
-    },
-    "WaitForLangDetectTranscribe": {
-      "Type": "Task",
-      "Resource": "arn:aws:states:::lambda:invoke.waitForTaskToken",
-      "Parameters": {
-        "FunctionName":"${SFAwaitNotificationArn}",
-        "Payload":{
-          "Input.$": "$",
-          "TaskToken.$":"$$.Task.Token"
-        }
-      },
-      "Retry": [{
-          "IntervalSeconds": 5,
-          "ErrorEquals": ["Lambda.Unknown"]
-      }],
-      "Next": "LangDetectionComplete?",
-      "Catch": [
-      {
-        "ErrorEquals": [ "States.ALL" ],
-        "Next": "TranscriptionFailed"
-      }
-      ]
-    },
-    "LangDetectionComplete?": {
-      "Type": "Choice",
-      "Choices": [
-        {
-          "Variable": "$.transcribeStatus",
-          "StringEquals": "COMPLETED",
-          "Next": "ParseDetectedLanguage"
-        },
-        {
-          "Variable": "$.transcribeStatus",
-          "StringEquals": "RETRY",
-          "Next": "TranscribeLangDetectClip"
-        }
-      ],
-      "Default": "TranscriptionFailed"
-    },
-    "ParseDetectedLanguage": {
-      "Comment": "Extracts the detected language code from the Transcribe job",
-      "Type": "Task",
-      "Resource": "${SFGetDetectedLanguageArn}",
-      "Retry": [{
-          "IntervalSeconds": 5,
-          "ErrorEquals": ["Lambda.Unknown"]
-      }],
-      "Next": "TranscribeAudio"
-    },
     "TranscribeStarted?": {
       "Type": "Choice",
       "Comment": "If a job was not started then we need to quit this workflow",

diff --git a/pca-server/cfn/lib/pca.template b/pca-server/cfn/lib/pca.template
@@ -118,20 +118,6 @@ Resources:
                 Resource: !Sub arn:aws:ssm:${AWS::Region}:${AWS::AccountId}:parameter/*
 
 
-  SFLanguageDetection:
-    Type: "AWS::Serverless::Function"
-    Properties:
-      CodeUri:  ../../src/pca
-      Handler: pca-aws-sf-language-detection.lambda_handler
-      MemorySize: 192
-      Timeout: 15
-      Layers:
-        - !Ref FFMPEGLayer
-      Environment:
-        Variables:
-          RoleArn: !GetAtt TranscribeRole.Arn
-      Role: !GetAtt TranscribeLambdaRole.Arn
-
   SFStartTranscribeJob:
     Type: "AWS::Serverless::Function"
     Properties:
@@ -147,15 +133,6 @@ Resources:
           AWS_DATA_PATH: "/opt/models"
       Role: !GetAtt TranscribeLambdaRole.Arn
 
-  SFGetDetectedLanguage:
-    Type: "AWS::Serverless::Function"
-    Properties:
-      CodeUri:  ../../src/pca
-      Handler: pca-aws-sf-get-detected-language.lambda_handler
-      Policies:
-        - arn:aws:iam::aws:policy/AmazonS3FullAccess
-        - arn:aws:iam::aws:policy/AmazonTranscribeFullAccess
-
   SFProcessTurn:
     Type: "AWS::Serverless::Function"
     Properties:
@@ -225,10 +202,8 @@ Resources:
                 Resource:
                   - !GetAtt SFProcessTurn.Arn
                   - !GetAtt SFStartTranscribeJob.Arn
-                  - !GetAtt SFLanguageDetection.Arn
                   - !GetAtt SFAwaitNotification.Arn
                   - !GetAtt SFTranscribeFailed.Arn
-                  - !GetAtt SFGetDetectedLanguage.Arn
         - PolicyName: CloudWatchLogs
           PolicyDocument:
             Statement:
@@ -252,10 +227,8 @@ Resources:
       DefinitionSubstitutions:
         SFProcessTurnArn: !GetAtt SFProcessTurn.Arn
         SFStartTranscribeJobArn: !GetAtt SFStartTranscribeJob.Arn
-        SFLanguageDetectionArn: !GetAtt SFLanguageDetection.Arn
         SFAwaitNotificationArn: !GetAtt SFAwaitNotification.Arn
         SFTranscribeFailedArn: !GetAtt SFTranscribeFailed.Arn
-        SFGetDetectedLanguageArn: !GetAtt SFGetDetectedLanguage.Arn
       LoggingConfiguration:
         Level: ERROR
         IncludeExecutionData: true

diff --git a/pca-server/src/pca/pca-aws-sf-get-detected-language.py b/pca-server/src/pca/pca-aws-sf-get-detected-language.py
diff --git a/pca-server/src/pca/pca-aws-sf-language-detection.py b/pca-server/src/pca/pca-aws-sf-language-detection.py