new requirements

requirements.txt

@@ -19,3 +19,5 @@ soundfile
 nose==1.3.7
 cardboardlint==1.3.0
 pylint==2.5.3
+fuzzywuzzy
+gdown

setup.py

@@ -98,6 +98,8 @@ requirements = {
         "nose==1.3.7",
         "cardboardlint==1.3.0",
         "pylint==2.5.3",
+        'fuzzywuzzy',
+        'gdown'
     ],
     'pip_install':[
         'tensorflow>=2.2.0',

vocoder/tf/convert_melgan_tflite.py

@@ -0,0 +1,34 @@
+# Convert Tensorflow Tacotron2 model to TF-Lite binary
+
+import argparse
+
+from TTS.utils.io import load_config
+from TTS.utils.text.symbols import symbols, phonemes
+from TTS.vocoder.tf.utils.generic_utils import setup_generator
+from TTS.vocoder.tf.utils.io import load_checkpoint
+from TTS.vocoder.tf.utils.tflite import convert_melgan_to_tflite
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--tf_model',
+                    type=str,
+                    help='Path to target torch model to be converted to TF.')
+parser.add_argument('--config_path',
+                    type=str,
+                    help='Path to config file of torch model.')
+parser.add_argument('--output_path',
+                    type=str,
+                    help='path to tflite output binary.')
+args = parser.parse_args()
+
+# Set constants
+CONFIG = load_config(args.config_path)
+
+# load the model
+model = setup_generator(CONFIG)
+model.build_inference()
+model = load_checkpoint(model, args.tf_model)
+
+# create tflite model
+tflite_model = convert_melgan_to_tflite(model, output_path=args.output_path)
+

vocoder/tf/utils/tflite.py

@@ -0,0 +1,31 @@
+import tensorflow as tf
+
+
+
+def convert_melgan_to_tflite(model,
+                                output_path=None,
+                                experimental_converter=True):
+    """Convert Tensorflow MelGAN model to TFLite. Save a binary file if output_path is
+    provided, else return TFLite model."""
+
+    concrete_function = model.inference_tflite.get_concrete_function()
+    converter = tf.lite.TFLiteConverter.from_concrete_functions(
+        [concrete_function])
+    converter.experimental_new_converter = experimental_converter
+    converter.optimizations = []
+    converter.target_spec.supported_ops = [
+        tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS
+    ]
+    tflite_model = converter.convert()
+    print(f'Tflite Model size is {len(tflite_model) / (1024.0 * 1024.0)} MBs.')
+    if output_path is not None:
+        # same model binary if outputpath is provided
+        with open(output_path, 'wb') as f:
+            f.write(tflite_model)
+        return None
+    return tflite_model
+
+def load_tflite_model(tflite_path):
+    tflite_model = tf.lite.Interpreter(model_path=tflite_path)
+    tflite_model.allocate_tensors()
+    return tflite_model