Merge branch 'master' of git.xpub.nl:/var/www/git.xpub.nl/repos/OuNoPo-make

Makefile

@@ -32,6 +32,7 @@ clean: ## removes output (target) files
 dirs: ## create the dirs in working dir
 	@-mkdir -p images/
 	@-mkdir -p output/
+	@-mkdir -p ocr/
 	@echo $(color_r)'Directories made': images/ output/
 
 
@@ -60,7 +61,7 @@ output/tagged-words.txt: ocr/output.txt ## Analyzes OCR'ed text using a Part of
 #  >>> import nltk
 #  >>> nltk.download('averaged_perceptron_tagger')
 
-output/chatbot.txt: ocr/output.txt ## DESCRIBE WHAT IT DOES. Dependencies: python3's chatterbot
+output/chatbot.txt: ocr/output.txt ## Comments a text with a simple chatbot. Dependencies: python3's chatterbot
 	cat $< | python3 src/textbotconversation.py $(@)
 
 
@@ -85,7 +86,6 @@ tts: output/chatbot.txt ocr/output.txt    ## text to speech. Dependencies: espea
 	@echo $(color_w)
 	cat $? | espeak
 
-ttstt: ocr/output.txt##text to speech, speech to text
-	cat $< | espeak -s 140 -v f2 --stdout > sound.wav
-	
 
+ttssr-human-only: ocr/output.txt ## Loop: text to speech-speech recognition. Dependencies: espeak, pocketsphinx
+	bash src/ttssr-loop-human-only.sh ocr/output.txt

src/audio_transcribe.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+
+import speech_recognition as sr
+import sys
+from termcolor import cprint, colored
+# obtain path to "english.wav" in the same folder as this script
+from os import path
+import random
+
+a1 = sys.argv[1] #same as $1 so when you run python3 audio_transcribe.py FOO ... argv[1] is FOO
+# print ("transcribing", a1, file=sys.stderr)
+AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), a1) # before it was english.wav
+# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "french.aiff")
+# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "chinese.flac")
+
+# print (AUDIO_FILE)
+# use the audio file as the audio source
+r = sr.Recognizer()
+with sr.AudioFile(AUDIO_FILE) as source:
+    audio = r.record(source)  # read the entire audio file
+
+color = ["white", "yellow"]
+on_color = ["on_red", "on_magenta", "on_blue", "on_grey"]
+# recognize speech using Sphinx
+
+try:
+    cprint( r.recognize_sphinx(audio), random.choice(color), random.choice(on_color))
+    # print( r.recognize_sphinx(audio))
+except sr.UnknownValueError:
+    print("uknown")
+except sr.RequestError as e:
+    print("Sphinx error; {0}".format(e))
+
+# sleep (1)
+
+# # recognize speech using Google Speech Recognition
+# try:
+#     # for testing purposes, we're just using the default API key
+#     # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+#     # instead of `r.recognize_google(audio)`
+#     print("Google Speech Recognition thinks you said " + r.recognize_google(audio))
+# except sr.UnknownValueError:
+#     print("Google Speech Recognition could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from Google Speech Recognition service; {0}".format(e))
+
+# # recognize speech using Google Cloud Speech
+# GOOGLE_CLOUD_SPEECH_CREDENTIALS = r"""INSERT THE CONTENTS OF THE GOOGLE CLOUD SPEECH JSON CREDENTIALS FILE HERE"""
+# try:
+#     print("Google Cloud Speech thinks you said " + r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS))
+# except sr.UnknownValueError:
+#     print("Google Cloud Speech could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from Google Cloud Speech service; {0}".format(e))
+
+# # recognize speech using Wit.ai
+# WIT_AI_KEY = "INSERT WIT.AI API KEY HERE"  # Wit.ai keys are 32-character uppercase alphanumeric strings
+# try:
+#     print("Wit.ai thinks you said " + r.recognize_wit(audio, key=WIT_AI_KEY))
+# except sr.UnknownValueError:
+#     print("Wit.ai could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from Wit.ai service; {0}".format(e))
+
+# # recognize speech using Microsoft Bing Voice Recognition
+# BING_KEY = "INSERT BING API KEY HERE"  # Microsoft Bing Voice Recognition API keys 32-character lowercase hexadecimal strings
+# try:
+#     print("Microsoft Bing Voice Recognition thinks you said " + r.recognize_bing(audio, key=BING_KEY))
+# except sr.UnknownValueError:
+#     print("Microsoft Bing Voice Recognition could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from Microsoft Bing Voice Recognition service; {0}".format(e))
+
+# # recognize speech using Houndify
+# HOUNDIFY_CLIENT_ID = "INSERT HOUNDIFY CLIENT ID HERE"  # Houndify client IDs are Base64-encoded strings
+# HOUNDIFY_CLIENT_KEY = "INSERT HOUNDIFY CLIENT KEY HERE"  # Houndify client keys are Base64-encoded strings
+# try:
+#     print("Houndify thinks you said " + r.recognize_houndify(audio, client_id=HOUNDIFY_CLIENT_ID, client_key=HOUNDIFY_CLIENT_KEY))
+# except sr.UnknownValueError:
+#     print("Houndify could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from Houndify service; {0}".format(e))
+
+# # recognize speech using IBM Speech to Text
+# IBM_USERNAME = "INSERT IBM SPEECH TO TEXT USERNAME HERE"  # IBM Speech to Text usernames are strings of the form XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
+# IBM_PASSWORD = "INSERT IBM SPEECH TO TEXT PASSWORD HERE"  # IBM Speech to Text passwords are mixed-case alphanumeric strings
+# try:
+#     print("IBM Speech to Text thinks you said " + r.recognize_ibm(audio, username=IBM_USERNAME, password=IBM_PASSWORD))
+# except sr.UnknownValueError:
+#     print("IBM Speech to Text could not understand audio")
+# except sr.RequestError as e:
+#     print("Could not request results from IBM Speech to Text service; {0}".format(e))

src/ttssr-loop-human-only.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+i=0;
+#cp $1 output/input0.txt
+echo "Read every new sentence out loud!"
+head -n 1 $1 > output/input0.txt
+while [[ $i -le 10 ]]
+	do echo $i
+	cat output/input$i.txt 
+	python3 src/write_audio.py src/sound$i.wav 2> /dev/null
+	play src/sound$i.wav repeat 5 2> /dev/null & #in the background the sound, without it all the sounds play one by one//2 is stderr
+	python3 src/audio_transcribe.py sound$i.wav > output/input$((i+1)).txt 2> /dev/null
+	sleep 
+	(( i++ ))
+done
+today=$(date +%Y-%m-%d);
+mkdir -p "output/ttssr.$today"
+mv -v output/input* output/ttssr.$today;
+mv -v src/sound* output/ttssr.$today;

src/wordtagger.py

@@ -1,26 +1,28 @@
 import nltk
 from sys import stdin, stdout
 
-# Step 1: define input and set up a list
+# Define input
 input = stdin.read()
-taggedwordlist = []
 
-string = input
+# FILTER FUNCTIONS
+# This function cuts a string into words. Then runs a POS tagger for each word. Returns a list with tags
+def postagger(string):
     words = nltk.word_tokenize(string)
     taggedwordlist = nltk.pos_tag(words)
 
     for word, pos in nltk.pos_tag(words):
         taggedwordlist = nltk.pos_tag(words)
-    # print('{0} is a {1}'.format(word,pos)) # Command out to print the analysis step
+        #print('{0} is a {1}'.format(word,pos)) # Comment out to print the analysis step
-
 
     taglist = [ pos for word,pos in taggedwordlist ]
-
     #print(taglist)
+    return taglist;
 
+# This function changes the tags to readable equivalents (NNP to noun for example)
+def postagger_readable(list):
     readabletaglist = []
 
-for tag in taglist:
+    for tag in list:
         if tag in {"NNP","NNS","NN","NNPS"}:
             readabletag = 'noun'
         elif tag in {'VB','VBD','VBG','VBN','VBP','VBZ'}:
@@ -67,5 +69,14 @@ for tag in taglist:
             readabletag = tag
 
         readabletaglist.append(readabletag)
+    return readabletaglist;
 
+
+# This function creates the output
+def main():
+    taglist = postagger(input)
+    readabletaglist = postagger_readable(taglist)
     stdout.write(' '.join(readabletaglist))
+    stdout.write('\n')
+
+main()

src/write_audio.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# https://github.com/Uberi/speech_recognition/blob/master/examples/write_audio.py
+# NOTE: this example requires PyAudio because it uses the Microphone class
+
+import speech_recognition as sr
+import sys
+from time import sleep
+
+a1 = sys.argv[1]
+
+# obtain audio from the microphone
+r = sr.Recognizer()
+with sr.Microphone() as source:
+    # print("Read every new sentence out loud!")
+    audio = r.listen(source)
+
+# sleep (1)
+#
+# # write audio to a RAW file
+# with open("microphone-results.raw", "wb") as f:
+#     f.write(audio.get_raw_data())
+
+# write audio to a WAV file
+with open(a1, "wb") as f:
+	f.write(audio.get_wav_data())