Update README.md

README.md

@@ -13,4 +13,49 @@ datasets:
 ## Install TensorFlowTTS
 ```
 pip install TensorFlowTTS
+```
+### Converting your Text to Mel Spectrogram
+```python
+import numpy as np
+import soundfile as sf
+import yaml
+import IPython.display as ipd
+
+import tensorflow as tf
+
+from tensorflow_tts.inference import AutoProcessor
+from tensorflow_tts.inference import TFAutoModel
+from tensorflow_tts.inference import AutoConfig
+
+processor = AutoProcessor.from_pretrained(pretrained_path="./processor.json")
+config = AutoConfig.from_pretrained("./config.yml")
+fastspeech2 = TFAutoModel.from_pretrained(
+    config=config, 
+    pretrained_path="./model.h5"
+)
+
+text = "xin chào đây là một ví dụ về chuyển đổi văn bản thành giọng nói"
+
+input_ids = processor.text_to_sequence(text)
+
+mel_before, mel_after, duration_outputs, _, _ = fastspeech2.inference(
+    input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
+    speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
+    speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
+    f0_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
+    energy_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
+)
+```
+
+#### Bonus: Convert Mel Spectrogram to Speech
+```python
+mb_melgan = TFAutoModel.from_pretrained("tensorspeech/tts-mb_melgan-ljspeech-en")
+
+audio_before = mb_melgan.inference(mel_before)[0, :, 0]
+audio_after = mb_melgan.inference(mel_after)[0, :, 0]
+
+sf.write("audio_before.wav", audio_before, 22050, "PCM_16")
+sf.write("audio_after.wav", audio_after, 22050, "PCM_16")
+
+ipd.Audio('audio_after.wav')
 ```