Update README.md

README.md

@@ -54,6 +54,38 @@ The model is available for use in the [NVIDIA NeMo](https://github.com/NVIDIA/Ne
 ### Inference
 For inference, you can follow our [Audio Codec Inference Tutorial](https://github.com/NVIDIA/NeMo/blob/main/tutorials/tts/Audio_Codec_Inference.ipynb) which automatically downloads the model checkpoint. Note that you will need to set the ```model_name``` parameter to "nvidia/low-frame-rate-speech-codec-22khz".
 
+In addition, you can use the code bellow that automatically download the checkpoint as well:
+
+```
+import librosa
+import torch
+import soundfile as sf
+from nemo.collections.tts.models import AudioCodecModel
+
+path_to_input_audio = ??? # path of the input audio
+path_to_output_audio = ??? # path of the reconstructed output audio
+
+# load audio codec
+nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/low-frame-rate-speech-codec-22khz").eval()
+
+# get discrete tokens from audio
+audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+audio_tensor = torch.from_numpy(audio).unsqueeze(dim=0).to(device)
+audio_len = torch.tensor([audio_tensor[0].shape[0]]).to(device)
+
+encoded_tokens, encoded_len = nemo_codec_model.encode(audio=audio_tensor, audio_len=audio_len)
+
+# Reconstruct audio from tokens
+reconstructed_audio, _ = nemo_codec_model.decode(tokens=encoded_tokens, tokens_len=encoded_len)
+
+# save reconstructed audio
+output_audio = reconstructed_audio.cpu().numpy().squeeze()
+sf.write(path_to_output_audio, output_audio, nemo_codec_model.sample_rate)
+
+```
+
 Alternatively, you can manually download the [checkpoint](https://huggingface.co/nvidia/low-frame-rate-speech-codec-22khz/resolve/main/low-frame-rate-speech-codec-22khz.nemo) and use the code below to make an inference on the model:
 
 ```
@@ -68,6 +100,7 @@ path_to_output_audio = ??? # path of the reconstructed output audio
 
 nemo_codec_model = AudioCodecModel.restore_from(restore_path=codec_path, map_location="cpu").eval()
 
+nemo_codec_model = AudioCodecModel.from_pretrained("nvidia/low-frame-rate-speech-codec-22khz").eval()
 # get discrete tokens from audio
 audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)