add information for inference (#4)

- add comments (66f6facf1de25d1680c50847a3d0dc5649d3204a)


Co-authored-by: Yingzhi Wang <yingzhi@users.noreply.huggingface.co>

README.md

@@ -48,7 +48,13 @@ hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", saved
 
 # Run TTS with text input
 input_text = "were the leaders in this luckless change; though our own Baskerville; who was at work some years before them; went much on the same lines;"
-mel_output, durations, pitch, energy = fastspeech2.encode_text([input_text])
+
+mel_output, durations, pitch, energy = fastspeech2.encode_text(
+  [input_text],
+  pace=1.0,        # scale up/down the speed
+  pitch_rate=1.0,  # scale up/down the pitch
+  energy_rate=1.0, # scale up/down the energy
+)
 
 # Running Vocoder (spectrogram-to-waveform)
 waveforms = hifi_gan.decode_batch(mel_output)
@@ -59,7 +65,12 @@ torchaudio.save('example_TTS_input_text.wav', waveforms.squeeze(1), 22050)
 
 # Run TTS with phoneme input
 input_phonemes = ['W', 'ER', 'DH', 'AH', 'L', 'IY', 'D', 'ER', 'Z', 'IH', 'N', 'DH', 'IH', 'S', 'L', 'AH', 'K', 'L', 'AH', 'S', 'CH', 'EY', 'N', 'JH', 'spn', 'DH', 'OW', 'AW', 'ER', 'OW', 'N', 'B', 'AE', 'S', 'K', 'ER', 'V', 'IH', 'L', 'spn', 'HH', 'UW', 'W', 'AA', 'Z', 'AE', 'T', 'W', 'ER', 'K', 'S', 'AH', 'M', 'Y', 'IH', 'R', 'Z', 'B', 'IH', 'F', 'AO', 'R', 'DH', 'EH', 'M', 'spn', 'W', 'EH', 'N', 'T', 'M', 'AH', 'CH', 'AA', 'N', 'DH', 'AH', 'S', 'EY', 'M', 'L', 'AY', 'N', 'Z', 'spn']
-mel_output, durations, pitch, energy = fastspeech2.encode_phoneme([input_phonemes])
+mel_output, durations, pitch, energy = fastspeech2.encode_phoneme(
+  [input_phonemes],
+  pace=1.0,        # scale up/down the speed
+  pitch_rate=1.0,  # scale up/down the pitch
+  energy_rate=1.0, # scale up/down the energy
+)
 
 # Running Vocoder (spectrogram-to-waveform)
 waveforms = hifi_gan.decode_batch(mel_output)