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

Makefile

@@ -57,7 +57,7 @@ tiffs: ## convert images/ to images-tiff/ Depends on IM
 	echo $(images)
 	for i in $(images); \
 	do tiff=`basename $$i .jpg`.tiff; \
-	convert -density 300 $$i images-tiff/$$tiff; \
+	convert -density 300 $$i -alpha on images-tiff/$$tiff; \
 	echo $$tiff; \
 	done;
 
@@ -110,12 +110,6 @@ else
 endif
 
 
-tts: output/chatbot.txt ocr/output.txt    ## text to speech. Dependencies: espeak
-	@echo $(color_r) speaking $?
-	@echo $(color_w)
-	cat $? | espeak
-
-
 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

@@ -1,19 +1,17 @@
 #!/usr/bin/env python3
+# https://github.com/Uberi/speech_recognition/blob/master/examples/audio_transcribe.py
 
 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:
@@ -21,8 +19,8 @@ with sr.AudioFile(AUDIO_FILE) as source:
 
 color = ["white", "yellow"]
 on_color = ["on_red", "on_magenta", "on_blue", "on_grey"]
-# recognize speech using Sphinx
 
+# recognize speech using Sphinx
 try:
     cprint( r.recognize_sphinx(audio), random.choice(color), random.choice(on_color))
     # print( r.recognize_sphinx(audio))
@@ -33,60 +31,3 @@ except sr.RequestError as 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

@@ -1,6 +1,5 @@
 #!/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 ]]
@@ -12,7 +11,7 @@ while [[ $i -le 10 ]]
 	sleep 
 	(( i++ ))
 done
-today=$(date +%Y-%m-%d);
+today=$(date +%Y%m%d.%H-%M);
 mkdir -p "output/ttssr.$today"
 mv -v output/input* output/ttssr.$today;
 mv -v src/sound* output/ttssr.$today;

src/write_audio.py

@@ -15,10 +15,6 @@ with sr.Microphone() as source:
     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: