add lib pydub

app.py

@@ -12,37 +12,40 @@ from scipy.io import wavfile
 import scipy
 
 # import soundfile as sf
-import audio2numpy as a2n
+# import audio2numpy as a2n
 import os
 
 import gradio as gr
 
-import audio2numpy
+# import audio2numpy
 # import numpy as np
 
-
-# https://stackoverflow.com/questions/53633177/how-to-read-a-mp3-audio-file-into-a-numpy-array-save-a-numpy-array-to-mp3
-def read(f, normalized=False):
-    """MP3 to numpy array"""
-    a = pydub.AudioSegment.from_mp3(f)
-    y = np.array(a.get_array_of_samples())
-    if a.channels == 2:
-        y = y.reshape((-1, 2))
-    if normalized:
-        return a.frame_rate, np.float32(y) / 2**15
-    else:
-        return a.frame_rate, y
+from pydub import AudioSegment
+from matplotlib import pyplot as plt
 
 
-def write(f, sr, x, normalized=False):
-    """numpy array to MP3"""
-    channels = 2 if (x.ndim == 2 and x.shape[1] == 2) else 1
-    if normalized:  # normalized array - each item should be a float in [-1, 1)
-        y = np.int16(x * 2 ** 15)
-    else:
-        y = np.int16(x)
-    song = pydub.AudioSegment(y.tobytes(), frame_rate=sr, sample_width=2, channels=channels)
-    song.export(f, format="mp3", bitrate="320k")
+# https://stackoverflow.com/questions/53633177/how-to-read-a-mp3-audio-file-into-a-numpy-array-save-a-numpy-array-to-mp3
+# def read(f, normalized=False):
+#     """MP3 to numpy array"""
+#     a = pydub.AudioSegment.from_mp3(f)
+#     y = np.array(a.get_array_of_samples())
+#     if a.channels == 2:
+#         y = y.reshape((-1, 2))
+#     if normalized:
+#         return a.frame_rate, np.float32(y) / 2**15
+#     else:
+#         return a.frame_rate, y
+#
+#
+# def write(f, sr, x, normalized=False):
+#     """numpy array to MP3"""
+#     channels = 2 if (x.ndim == 2 and x.shape[1] == 2) else 1
+#     if normalized:  # normalized array - each item should be a float in [-1, 1)
+#         y = np.int16(x * 2 ** 15)
+#     else:
+#         y = np.int16(x)
+#     song = pydub.AudioSegment(y.tobytes(), frame_rate=sr, sample_width=2, channels=channels)
+#     song.export(f, format="mp3", bitrate="320k")
 
 
 # Load the model.
@@ -86,7 +89,28 @@ def inference(audio):
     if debug: print(f'read, wav_file_name: {wav_file_name}')
 
     if wav_file_name.endswith('.mp3'):
-        wav_data, sample_rate = a2n.audio_from_file(wav_file_name)
+        # https://stackoverflow.com/questions/16634128/how-to-extract-the-raw-data-from-a-mp3-file-using-python
+        # This will open and read the audio file with pydub.  Replace the file path with
+        # your own file.
+        audio_file = AudioSegment.from_file(wav_file_name)
+
+        # Set up a list for us to dump PCM samples into, and create a 'data' variable
+        # so we don't need to type audio_file._data again
+        data = audio_file._data
+        pcm16_signed_integers = []
+
+        # This loop decodes the bytestring into PCM samples.
+        # The bytestring is a stream of little-endian encoded signed integers.
+        # This basically just cuts each two-byte sample out of the bytestring, converts
+        # it to an integer, and appends it to the list of samples.
+        for sample_index in range(len(data) // 2):
+            sample = int.from_bytes(data[sample_index * 2:sample_index * 2 + 2], 'little', signed=True)
+            pcm16_signed_integers.append(sample)
+        if debug: print(f'pcm16_signed_integers: {pcm16_signed_integers}')
+
+        # Now plot the samples!
+        # plt.plot(pcm16_signed_integers)
+        # plt.show()
     else:
         sample_rate, wav_data = wavfile.read(wav_file_name, 'rb')
     

requirements.txt

@@ -3,4 +3,4 @@ tensorflow_hub
 numpy
 scipy
 gradio
-audio2numpy
+pydub