Text gen implementation

Indexing/text_gen.py

+import speech_recognition as sr
+import subprocess
+import os
+import sys
+
+PYTHONIOENCODING = "UTF-8"
+
+FOLDER_AUDIO = "audio_input"
+FOLDER_TEXT = "text_output"
+LANGUAGE = "en-US"
+
+
+# print("starting...")
+#
+# if not os.path.isdir(FOLDER_AUDIO):
+#     os.mkdir(FOLDER_AUDIO)
+#
+# if not os.path.isdir(FOLDER_TEXT):
+#     os.mkdir(FOLDER_TEXT)
+#
+# paths = [os.path.join(FOLDER_AUDIO, nome) for nome in os.listdir(FOLDER_AUDIO)]
+# files = [arq for arq in paths if os.path.isfile(arq)]
+# wav_files = [arq for arq in files if arq.lower().endswith(".wav")]
+#
+# for filename in wav_files:
+#     r = sr.Recognizer()
+#     with sr.AudioFile(filename) as source:
+#         audio = r.record(source)
+#
+#     command = r.recognize_google(audio, language='en-IN', show_all=True)
+#     print(command)
+#
+#     print("running file {}".format(filename))
+#
+#     filefinal = filename.split("audio_input/")[1].split(".wav")[0]
+#     filefinal = '{}/{}.txt'.format(FOLDER_TEXT, filefinal)
+#     with open(filefinal, 'w') as arq:
+#         arq.write(str(command))
+#
+#     print("create a new file {}".format(filefinal))
+#
+# print("finish")
+
+
+def convert_audio_to_text(filename):
+    r = sr.Recognizer()
+    with sr.AudioFile(filename) as source:
+        audio = r.record(source)
+
+    try:
+        command = r.recognize_google(audio, language='en-IN', show_all=True)
+        print(command["alternative"][0]["transcript"])
+        return command["alternative"][0]["transcript"]
+
+    except:
+        return 'did not convert'
+
+# convert_audio_to_text('audio_input/3.wav')