refractoring and more tests

multilang_translator/text_to_speech/text_to_speech.py

@@ -2,6 +2,7 @@ import os
 import subprocess
 import time
 import logging as log
+import wave
 
 TTS_DIR = os.path.join(os.path.dirname(__file__))
 
@@ -11,9 +12,15 @@ def synthesize(text, model="en_US-lessac-medium", output_file="out.wav"):
     os.chdir(TTS_DIR)
     start = time.time()
     ret = subprocess.run(['piper', '--model', model, '--output_file', output_file], input=text.encode('utf-8'), check=True)
-    log.info("Running piper took %s s", round(time.time() - start, 3))
+
+    with wave.open(output_file, "rb") as wf:
+        frames = wf.getnframes()
+        rate = wf.getframerate()
+
+        length_in_seconds = round(frames / rate, 1)
+        log.info(f"Audio length: {length_in_seconds} s")
+
     os.chdir(pwd)
+    log.info("Running piper took %s s", round(time.time() - start, 3))
 
-
-if __name__ == "__main__":
-    synthesize("Hello, how are you?", "en_US-lessac-medium", "hello.wav")
+    return length_in_seconds