rename speech recorder and update

speech-recorder.py

@@ -1,49 +0,0 @@
-import wave
-from pyaudio import PyAudio,paInt16
-
-framerate=16000
-NUM_SAMPLES=2000
-channels=1
-sampwidth=2
-TIME=10
-def save_wave_file(filename,data):
-    '''save the date to the wavfile'''
-    wf=wave.open(filename,'wb')
-    wf.setnchannels(channels)
-    wf.setsampwidth(sampwidth)
-    wf.setframerate(framerate)
-    wf.writeframes(b"".join(data))
-    wf.close()
-
-def my_record():
-    pa=PyAudio()
-    stream=pa.open(format = paInt16,channels=1,
-                   rate=framerate,input=True,
-                   frames_per_buffer=NUM_SAMPLES)
-    my_buf=[]
-    count=0
-    while count<TIME*8:#控制录音时间
-        string_audio_data = stream.read(NUM_SAMPLES)
-        my_buf.append(string_audio_data)
-        count+=1
-        print('.')
-    save_wave_file('01.wav',my_buf)
-    stream.close()
-
-chunk=2014
-def play():
-    wf=wave.open(r"01.wav",'rb')
-    p=PyAudio()
-    stream=p.open(format=p.get_format_from_width(wf.getsampwidth()),channels=
-    wf.getnchannels(),rate=wf.getframerate(),output=True)
-    while True:
-        data=wf.readframes(chunk)
-        if data=="":break
-        stream.write(data)
-    stream.close()
-    p.terminate()
-
-if __name__ == '__main__':
-    my_record()
-    print('Over!') 
-    play()

speech_recorder.py

@@ -0,0 +1,83 @@
+import pyaudio
+import wave
+
+
+def record_wave(wavfile,
+                duration=10,
+                channels=1,
+                sampling_rate=16000,
+                sampling_bits=16,
+                chunk_size=1024,
+                keyboard_interrupt='keep_audio'):
+    """Record audio using the default audio device by PyAudio and Wave"""
+
+    format_ = None
+    if sampling_bits == 8:
+        format_ = pyaudio.paInt8
+    if sampling_bits == 16:
+        format_ = pyaudio.paInt16
+    elif sampling_bits == 24:
+        format_ = pyaudio.paInt24
+    elif sampling_bits == 32:
+        format_ = pyaudio.paFloat32
+    else:
+        raise ValueError('Unsupported sampling bits')
+
+    p = pyaudio.PyAudio()
+    stream = p.open(format=format_,
+                    channels=channels,
+                    rate=sampling_rate,
+                    input=True,
+                    frames_per_buffer=chunk_size)
+
+    frames = []
+
+    print('Start to record with {}-seconds audio\n'
+          'Type Ctrl-C to get an early stop (a shorter audio)'
+          .format(duration))
+    try:
+        for _ in range(0, int(sampling_rate / chunk_size * duration)):
+            data = stream.read(chunk_size)
+            frames.append(data)
+            print('.', end='', flush=True)
+    except KeyboardInterrupt:
+        if keyboard_interrupt == 'keep_audio':
+            used_seconds = int(len(frames) * chunk_size / sampling_rate)
+            print('\n-*- Early stop with {} seconds'.format(used_seconds))
+        else:
+            raise
+    print('\nRecording finished')
+
+    stream.stop_stream()
+    stream.close()
+    p.terminate()
+
+    print('Convert PCM frames to WAV... ', end='')
+    wf = wave.open(wavfile, 'wb')
+    wf.setnchannels(channels)
+    wf.setsampwidth(p.get_sample_size(format_))
+    wf.setframerate(sampling_rate)
+    wf.writeframes(b''.join(frames))
+    wf.close()
+    print('OK')
+
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
+
+    parser = ArgumentParser(description='Simple Wave Audio Recorder',
+                            formatter_class=ArgumentDefaultsHelpFormatter)
+    parser.add_argument('-d', '--duration', type=int,
+                        default=10, help='maximum duration in seconds')
+    parser.add_argument('-r', '--sampling-rate', type=int,
+                        default=16000, help='sampling rate')
+    parser.add_argument('-b', '--sampling-bits', type=int,
+                        default=16, choices=(8, 16, 24, 32), help='sampling bits')
+    parser.add_argument('-c', '--channels', type=int,
+                        default=1, help='audio channels')
+    parser.add_argument('output', nargs='?', default='output.wav', help='audio file to store audio stream')
+    args = parser.parse_args()
+    record_wave(args.output, duration=args.duration,
+                channels=args.channels,
+                sampling_bits=args.sampling_bits,
+                sampling_rate=args.sampling_rate)