almost added speakers

FirstTry/speech_recognition_try.py

@@ -15,35 +15,47 @@
 """
 
 import speech_recognition as sr
+import soundcard as sc
+from scipy.io.wavfile import write
+import numpy as np
+
+din = sc.all_microphones(include_loopback=True)[1]
+
+def speech_to_text_from_speaker(speaker,time = 100_000,samplerate = 48000,lang = 'ru-RU'):
+    with speaker.recorder(samplerate=samplerate) as mic:
+        print('Listen')
+        dt = mic.record(time)
+        dt =  np.int16(dt * (32767/np.max(np.abs(np.array([dt.min(),dt.max()])))))
+        print('Okay. Wait')
+        write("tmp.wav", samplerate, dt)
+
+    return speech_to_text_from_wav(lang)
+
 
-def speech_to_text_from_wav():
+
+def speech_to_text_from_wav(lang = 'ru-RU', file = 'tmp.wav'):
 
     # Initialize recognizer class (for recognizing the speech)
     r = sr.Recognizer()
 
     # Reading Audio file as source
     # listening the audio file and store in audio_text variable
 
-    with sr.AudioFile('english.wav') as source:
+    with sr.AudioFile(file) as source:
 
         audio_text = r.listen(source)
 
     # recoginize_() method will throw a request error if the API is unreachable, hence using exception handling
         try:
-
-            # using google speech recognition
-            text = r.recognize_google(audio_text)
-            print('Converting audio transcripts into text ...')
-            print(text)
-
-        except:
-             print('Sorry.. run again...')
+            return r.recognize_google(audio_text, language = lang)
+        except Exception as e:
+            print(e)
+            return 'bad result of recognition'
 
 
 def speech_to_text_from_micro(lang = 'ru-RU'):
     r = sr.Recognizer()
 
-
     # Reading Microphone as source
     # listening the speech and store in audio_text variable
 
@@ -52,46 +64,63 @@ def speech_to_text_from_micro(lang = 'ru-RU'):
         #energy threshold based on the surrounding noise level 
         r.adjust_for_ambient_noise(source, 0.5) 
 
-        print("Talk")
+        print(f"TALK ({lang[:2]})")
         audio_text = r.listen(source)
-        print("Time over, thanks")
+        print("Okay. Stop talking")
         # recoginize_() method will throw a request error if the API is unreachable, hence using exception handling
-        
-        try:
-            # using google speech recognition
-            print("Text: "+r.recognize_google(audio_text, language = lang))
-        except:
-            print("could not understand audio")
+
+    try:
+        return r.recognize_google(audio_text, language = lang)
+    except Exception as e:
+        print(e)
+        return 'bad result of recognition'
 
 
 speech_to_text_from_micro()
+speech_to_text_from_wav()
 
+speech_to_text_from_speaker(din,time=100000,lang = 'ru-RU')
 
 
 
 
 
+from scipy.io.wavfile import write
+samplerate = 100000; fs = 1000
+t = np.linspace(0., 1., samplerate)
+amplitude = np.iinfo(np.int16).max
+data = amplitude * np.sin(2. * np.pi * fs * t)
+write("example.wav", samplerate, data)
 
 
+import numpy as np
+from scipy.io.wavfile import write
 
+data = np.random.uniform(-1,1,44100) # 44100 random samples between -1 and 1
+scaled = np.int16(data/np.max(np.abs(data)) * 32767)
+write('test.wav', 44100, scaled)
 
 
+with din.recorder(samplerate=48000) as mic:
+    print('Listen')
+    dt = mic.record(100_000)
+    dt = np.int16(dt/np.max(np.abs(dt)) * 32767)
+    print('Okay')
+    write("tmp.wav", 48000, dt)
 
 
 
 
 
+dt = np.random.rand(50000,500)
 
+%timeit r = np.int16(dt/np.max(np.abs(dt)) * 32767)
 
+%timeit r = np.int16(dt * (32767/np.max(np.abs(dt))))
 
+%timeit r = np.array(dt * (32767/np.max(np.abs(dt))),dtype='int16')
 
-
-
-
-
-
-
-
+%timeit r = np.int16(dt * (32767/np.max(np.abs(np.array([dt.min(),dt.max()])))))
 
 
 

SecondTry/soundcardtest.py

@@ -32,12 +32,38 @@
 # alternatively, get a `Recorder` and `Player` object
 # and play or record continuously:
 with default_mic.recorder(samplerate=48000) as mic, default_speaker.player(samplerate=48000) as sp:
-    for _ in range(100):
+    for _ in range(200):
         data = mic.record(numframes=1024)
         sp.play(data)
 
 
 
+import scipy
+
+din = sc.all_microphones(include_loopback=True)[1]
+with din.recorder(samplerate=48000) as mic, default_speaker.player(samplerate=48000) as sp:
+    for _ in range(1):
+        print('play')
+        data = mic.record(numframes=48000)
+        print('stop')
+        scipy.io.wavfile.write("tmp.wav", 48000, data)
+        sp.play(data)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+