test for synthesize.py

TTS/bin/synthesize.py

@@ -27,7 +27,7 @@ def main():
     parser = argparse.ArgumentParser(
         description="""Synthesize speech on command line.\n\n"""
         """You can either use your trained model or choose a model from the provided list.\n\n"""
-        """If you don't specify any models, then it uses LJSpeech based English models\n\n"""
+        """If you don't specify any models, then it uses LJSpeech based English model.\n\n"""
         """
     # Example Runs:
 
@@ -180,7 +180,7 @@ def main():
     args = parser.parse_args()
 
     # print the description if either text or list_models is not set
-    if args.text is None and not args.list_models:
+    if args.text is None and not args.list_models and not args.list_speaker_idxs:
         parser.parse_args(["-h"])
 
     # load model manager

tests/__init__.py

@@ -14,3 +14,8 @@ def get_tests_input_path():
 def get_tests_output_path():
     """Returns the path to the directory for test outputs."""
     return os.path.join(get_tests_path(), "outputs")
+
+
+def run_cli(command):
+    exit_status = os.system(command)
+    assert exit_status == 0, f" [!] command `{command}` failed."

tests/test_speaker_manager.py

@@ -5,9 +5,9 @@ import numpy as np
 import torch
 
 from tests import get_tests_input_path
-from TTS.tts.utils.speakers import SpeakerManager
 from TTS.speaker_encoder.model import SpeakerEncoder
 from TTS.speaker_encoder.utils.generic_utils import save_checkpoint
+from TTS.tts.utils.speakers import SpeakerManager
 from TTS.utils.audio import AudioProcessor
 from TTS.utils.io import load_config
 

tests/test_synthesize.py

@@ -0,0 +1,28 @@
+import os
+
+from tests import get_tests_output_path, run_cli
+
+
+def test_synthesize():
+    """Test synthesize.py with diffent arguments."""
+    output_path = os.path.join(get_tests_output_path(), "output.wav")
+    run_cli("tts --list_models")
+
+    # single speaker model
+    run_cli(f'tts --text "This is an example." --out_path "{output_path}"')
+    run_cli(
+        "tts --model_name tts_models/en/ljspeech/speedy-speech-wn"
+        f'--text "This is an example." --out_path "{output_path}"'
+    )
+    run_cli(
+        "tts --model_name tts_models/en/ljspeech/speedy-speech-wn  "
+        "--vocoder_name vocoder_models/en/ljspeech/multiband-melgan "
+        f'--text "This is an example." --out_path "{output_path}"'
+    )
+
+    # multi-speaker model
+    run_cli("tts --model_name tts_models/en/vctk/sc-glow-tts --list_speaker_idxs")
+    run_cli(
+        f'tts --model_name tts_models/en/vctk/sc-glow-tts --speaker_idx "p304"'
+        f'--text "This is an example." --out_path "{output_path}"'
+    )