replace tensorflow based functionality with non tf stuff

google_perch_tflite/model.py

@@ -9,6 +9,7 @@ from iSparrow import ModelBase
 
 import numpy as np
 from pathlib import Path
+from scipy.special import softmax
 
 class Model(ModelBase): 
     """
@@ -70,7 +71,7 @@ class Model(ModelBase):
 
         logits = self.model.get_tensor(self.output_layer_index)
 
-        confidence = tf.nn.softmax(logits).numpy()
+        confidence = softmax(logits)
 
         return confidence
 

google_perch_tflite/preprocessor.py

@@ -19,7 +19,6 @@ class Preprocessor(ppb.PreprocessorBase):
         )
 
     def process_audio_data(self, rawdata: np.array)->np.array: 
-        self.chunks = []
 
         # raise when sampling rate is unequal.
         if self.actual_sampling_rate != self.sample_rate:
@@ -27,13 +26,29 @@ class Preprocessor(ppb.PreprocessorBase):
                 "Sampling rate is not the desired one. Desired sampling rate: {self.sample_rate}, actual sampling rate: {self.actual_sampling_rate}"
             )
 
-        frame_length = int(self.sample_secs * self.sample_rate)
-        step_length = int(self.sample_secs - self.overlap) * self.sample_rate
+        seconds = self.sample_secs
+        minlen = 1.5
+
+        self.chunks = []
+
+        for i in range(
+            0, len(rawdata), int((seconds - self.overlap) * self.sample_rate)
+        ):
+
+            split = rawdata[i : (i + int(seconds * self.actual_sampling_rate))]
+
+            # End of signal?
+            if len(split) < int(minlen * self.actual_sampling_rate):
+                break
 
-        self.chunks = tf_split_signal_into_chunks(
-            rawdata, frame_length, step_length, pad_end=True
-        ).numpy()
+            # Signal chunk too short? Fill with zeros.
+            if len(split) < int(self.actual_sampling_rate * seconds):
+                temp = np.zeros((int(self.actual_sampling_rate * seconds)))
+                temp[: len(split)] = split
+                split = temp
 
+            self.chunks.append(split)
+            
         print(
             "process audio data google: complete, read ",
             str(len(self.chunks)),