Update README.md

README.md

@@ -41,7 +41,7 @@ The following is an example of converting text-to-speech with the speaker voice
 **Note:** 
 - The model generates speech at a rate of 22050 Hz, but it's important to note that the input signal, crucial for capturing speaker identities, must be sampled at 16kHz.
 
-```
+```python
 import torchaudio
 from speechbrain.inference.TTS import MSTacotron2
 from speechbrain.inference.vocoders import HIFIGAN
@@ -66,7 +66,7 @@ torchaudio.save("synthesized_sample.wav", waveforms.squeeze(1).cpu(), 22050)
 
 If you want to generate a random voice, you can use the following:
 
-```
+```python
 import torchaudio
 from speechbrain.inference.TTS import MSTacotron2
 from speechbrain.inference.vocoders import HIFIGAN
@@ -92,7 +92,7 @@ torchaudio.save("synthesized_sample.wav", waveforms.squeeze(1).cpu(), 22050)
 If you want to generate multiple sentences in one-shot, you can do it this way:
 Note: The model internally reorders the input texts in the decreasing order of their lengths.
 
-```
+```python
 import torchaudio
 from speechbrain.inference.TTS import MSTacotron2
 from speechbrain.inference.vocoders import HIFIGAN