add some pyaudio test files
[scannr.git] / snd.py
blob:a/snd.py -> blob:b/snd.py
--- a/snd.py
+++ b/snd.py
@@ -1,15 +1,12 @@
-""" Record a few seconds of audio and save to a WAVE file. 
+""" Record a few seconds of audio and save to a WAVE file.
 Based on http://stackoverflow.com/questions/892199/detect-record-audio-in-python/6743593#6743593
 """
 
 import pyaudio
 import wave
 import sys
-import audioop # http://docs.python.org/library/audioop
-from os.path import exists
 from array import array
 from struct import unpack, pack
-import threading
 from pydispatch import dispatcher
 
 THRESHOLD = 500
@@ -17,11 +14,11 @@
 FORMAT = pyaudio.paInt16
 RATE = 44100
 if sys.platform.startswith('darwin'):
-	CHANNELS = 2
+    CHANNELS = 2
 elif sys.platform.startswith('win32'):
-	CHANNELS = 1
+    CHANNELS = 1
 
-MAX_SILENT = 30
+MAX_SILENT = 80
 
 def is_silent(L):
     "Returns `True` if below the 'silent' threshold"
@@ -29,24 +26,27 @@
     "print max(L) < THRESHOLD"
     return max(L) < THRESHOLD
 
+
 def normalize(L):
     "Average the volume out"
     MAXIMUM = 16384
-    times = float(MAXIMUM)/max(abs(i) for i in L)
+    times = float(MAXIMUM) / max(abs(i) for i in L)
 
     LRtn = array('h')
     for i in L:
-        LRtn.append(int(i*times))
+        LRtn.append(int(i * times))
     return LRtn
+
 
 def trim(L):
     "Trim the blank spots at the start and end"
+
     def _trim(L):
         snd_started = False
         LRtn = array('h')
 
         for i in L:
-            if not snd_started and abs(i)>THRESHOLD:
+            if not snd_started and abs(i) > THRESHOLD:
                 snd_started = True
                 LRtn.append(i)
 
@@ -63,27 +63,29 @@
     L.reverse()
     return L
 
+
 def add_silence(L, seconds):
     "Add silence to the start and end of `L` of length `seconds` (float)"
-    LRtn = array('h', [0 for i in xrange(int(seconds*RATE))])
+    LRtn = array('h', [0 for i in xrange(int(seconds * RATE))])
     LRtn.extend(L)
-    LRtn.extend([0 for i in xrange(int(seconds*RATE))])
+    LRtn.extend([0 for i in xrange(int(seconds * RATE))])
     return LRtn
+
 
 def record():
     """
-    Record a word or words from the microphone and 
+    Record a word or words from the microphone and
     return the data as an array of signed shorts.
 
-    Normalizes the audio, trims silence from the 
-    start and end, and pads with 0.5 seconds of 
-    blank sound to make sure VLC et al can play 
+    Normalizes the audio, trims silence from the
+    start and end, and pads with 0.5 seconds of
+    blank sound to make sure VLC et al can play
     it without getting chopped off.
     """
     p = pyaudio.PyAudio()
-    stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, 
-                    input=True,
-                    frames_per_buffer=CHUNK_SIZE)
+    stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE,
+        input=True,
+        frames_per_buffer=CHUNK_SIZE)
 
     num_silent = 0
     snd_started = False
@@ -91,8 +93,13 @@
     LRtn = array('h')
 
     while 1:
-        data = stream.read(CHUNK_SIZE)
-        L = unpack('<' + ('h'*(len(data)/2)), data) # little endian, signed short
+        try:
+            data = stream.read(CHUNK_SIZE)
+        except IOError as ex:
+            if ex[1] != pyaudio.paInputOverflowed:
+                raise
+            data = '\x00' * CHUNK_SIZE
+        L = unpack('<' + ('h' * (len(data) / 2)), data) # little endian, signed short
         L = array('h', L)
 
         silent = is_silent(L)
@@ -100,11 +107,13 @@
 
         if silent and snd_started:
             num_silent += 1
-            print num_silent
+            #print num_silent
         elif not silent and not snd_started:
-            dispatcher.send( signal='SND_STARTED')
+            dispatcher.send(signal='SND_STARTED')
             snd_started = True
             print snd_started
+        if snd_started and not silent:
+            num_silent = 0
         if snd_started:
             LRtn.extend(L)
         if snd_started and num_silent > MAX_SILENT:
@@ -120,10 +129,11 @@
     LRtn = add_silence(LRtn, 0.5)
     return sample_width, LRtn
 
+
 def record_to_file(path):
     "Records from the microphone and outputs the resulting data to `path`"
     sample_width, data = record()
-    data = pack('<' + ('h'*len(data)), *data)
+    data = pack('<' + ('h' * len(data)), *data)
 
     wf = wave.open(path, 'wb')
     wf.setnchannels(CHANNELS)
@@ -131,14 +141,12 @@
     wf.setframerate(RATE)
     wf.writeframes(data)
     wf.close()
-    print("done - result written to "+path)
+    print("done - result written to " + path)
     del data
 
 
+if __name__ == '__main__':
+    filename = 'demo.wav'
+    record_to_file(filename)
+    print("done - result written to " + filename)
 
-
-if __name__ == '__main__':
-	filename = 'demo.wav'
-        record_to_file(filename)
-        print("done - result written to "+filename)
-