AttributeError: 'WaveUNetModelOutputs' object has no attribute 'output'

[karim23657]

@will-rice , I just got this error,I attached my audio file:
p232.wav.zip

code:

import torch
import torchaudio
from denoisers import WaveUNetModel
from tqdm import tqdm

model = WaveUNetModel.from_pretrained("wrice/waveunet-vctk-24khz")

audio, sr = torchaudio.load("/content/p2325.wav")

if sr != model.config.sample_rate:
    audio = torchaudio.functional.resample(audio, sr, model.config.sample_rate)

chunk_size = model.config.max_length

padding = abs(audio.size(-1) % chunk_size - chunk_size)
padded = torch.nn.functional.pad(audio, (0, padding))

clean = []
for i in tqdm(range(0, padded.shape[-1], chunk_size)):
    audio_chunk = padded[:, i:i + chunk_size]
    with torch.no_grad():
        clean_chunk = model(audio_chunk[None]).audio
    clean.append(clean_chunk.squeeze(0))

denoised = torch.concat(clean, 1)[:, :audio.shape[-1]]

error:

0%|          | 0/1 [00:01<?, ?it/s]

AttributeError        
[p232.wav.zip](https://github.com/will-rice/denoisers/files/14550543/p232.wav.zip)
                    Traceback (most recent call last)
     22         # a=model(audio_chunk[None])
     23         # print(a)
---> 24         clean_chunk = model(audio_chunk[None]).output.audio
     25         # clean_chunk = model(audio_chunk[None]).audio
     26     clean.append(clean_chunk.squeeze(0))

AttributeError: 'WaveUNetModelOutputs' object has no attribute 'output'

[will-rice]

it should be .audio not .output.audio

[karim23657]

@will-rice , I used .audio in my code, but in issue I pasted my previous console output here,
But now i attached a jupyter notebook to reproduce error:

this is test audio file:
p232.wav.zip

[will-rice]

I didn't publish a new release with the .audio change. A work around is using .logits instead of .audio for version 0.1.6. I'm publishing a release right now with the correction. The latest version 0.1.7 will use .audio

[will-rice]

@karim23657 were you able to get this working?

[karim23657]

@will-rice , thank you . Now working.

import IPython
IPython.display.Audio(denoised.numpy(), rate=model.config.sample_rate)