-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathspeech
More file actions
56 lines (51 loc) · 1.28 KB
/
speech
File metadata and controls
56 lines (51 loc) · 1.28 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
# sachinpythonclass
'''
#Speech to txt from server
import speech_recognition as sr
print(sr.__version__)
r=sr.Recognizer()
harvard = sr.AudioFile('01 Baarish - Half Girlfriend (Ash King) 190Kbps.mp3')
with harvard as source:
audio = r.record(source)
print(type(audio))
print(r.recognize_google(audio,language='hi-HI'))
print(r.recognize_google(audio))
'''
# MIcrophone Detection
#import pyaudio
import speech_recognition as sr
r= sr.Recognizer()
mic=sr.Microphone()
harvard = sr.Microphone.list_microphone_names()
for source in harvard:
print(source)
# Recording!!
import pyaudio
import wave
CHUNK =1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 4100
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = 'output.wav'
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input =True,
frames_per_buffer=CHUNK)
print("# recording")
frames=[]
for i in range(0, int(RATE/CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
frames.append(data)
print("* done recording")
stream.stop_stream()
stream.close()
p.terminate()
wf=wave.open(WAVE_OUTPUT_FILENAME,'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()