Update README.md

README.md

@@ -59,11 +59,11 @@ import torch
 import soundfile as sf
 from nemo.collections.tts.models import AudioCodecModel
 
-codec_path = ??? # set here the model .nemo checkpoint path
+model_name = "nvidia/audio-codec-22khz"
 path_to_input_audio = ??? # path of the input audio
 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(model_name).eval()
 
 # get discrete tokens from audio
 audio, _ = librosa.load(path_to_input_audio, sr=nemo_codec_model.sample_rate)
@@ -72,10 +72,11 @@ 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)
+with torch.no_grad():
+  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()
@@ -106,7 +107,7 @@ The NeMo Audio Codec is trained on a total of 28.7k hrs of speech data from 105
 
 We evaluate our codec using several objective audio quality metrics. We evaluate [ViSQOL](https://github.com/google/visqol) and [PESQ](https://lightning.ai/docs/torchmetrics/stable/audio/perceptual_evaluation_speech_quality.html) for perception quality, [ESTOI](https://ieeexplore.ieee.org/document/7539284) for intelligbility, mel spectrogram and STFT distances for spectral reconstruction accuracy, and [SI-SDR](https://arxiv.org/abs/1811.02508) for phase reconstruction accuracy. Metrics are reported on the test set for both the MLS English and CommonVoice data. The model has not been trained or evaluated on non-speech audio.
 
-| Dataset     | ViSQOL     |PESQ        |ESTOI       |Mel Distance |STFT Distance|SI-SDR|
+| Dataset     | ViSQOL     |PESQ        |ESTOI       |Mel Distance |STFT Distance|SI-SDR       |
 |:-----------:|:----------:|:----------:|:----------:|:-----------:|:-----------:|:-----------:|
 | MLS English | 4.50       | 3.69       | 0.94       | 0.066       | 0.033       | 8.33        |
 | CommonVoice | 4.53       | 3.55       | 0.93       | 0.100       | 0.057       | 7.63        |